Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden. It reveals that the new column is empty, which is useful, but does not disclose permissions, side effects on existing columns, whether the board must exist, or what happens on success. For a mutation tool with zero annotation coverage, this is a significant gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with no filler. Every word contributes to stating the action and the target resource, making it appropriately sized for a simple creation tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is simple, and the schema covers all parameters with full descriptions, so an agent can determine the required inputs. However, with no annotations and no output schema, the description should ideally mention prerequisites or side effects. It is minimally adequate but leaves behavioral context thin.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so boardId, name, and index are fully documented in the schema, including the index default. The description adds no parameter-level meaning beyond what the schema already provides, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: 'Add an empty column to a board.' It clearly distinguishes add from sibling operations like rename_column, reorder_column, and delete_column. However, it does not explicitly name alternatives or scope boundaries, so it falls short of the highest clarity tier.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus alternatives such as reorder_column or update_column_agents. No prerequisites, exclusions, or usage context are provided. The agent must infer usage from the tool name alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full disclosure burden. It reveals the optional @mentions and clickable option buttons, but says nothing about side effects such as notifying mentioned users, attribution behavior, or what the call returns.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence with no filler; the core action comes first and the optional capabilities follow.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a six-parameter mutation tool with no annotations and no output schema, the description is thin – it omits permission requirements, side effects like notifications, and any indication of the return value. It is adequate to identify the action but not to call it confidently.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all six parameters are already documented, including text markdown support, mentions, and options. The description merely repeats the mentions/options concepts, adding no syntax or format detail beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource ('add a comment to a card') and names the two optional capabilities. It is clearly distinguishable from get_comments, though it doesn't explicitly note sibling relationships beyond the read/write split.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this versus alternatives, no prerequisites (e.g., board/card must exist), and no exclusions. Usage is only implied by the tool name and verb.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden of behavioral disclosure. It states that it automatically finds the column containing the card, which is a useful behavioral detail, but it does not mention permissions, side effects, or what happens if the sticker already exists. This leaves significant gaps for a mutation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two concise sentences with zero waste, front-loading the core action and then providing a key behavioral detail. Every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutation tool with no annotations and no output schema, the description is incomplete. It lacks information about required permissions, error conditions (e.g., invalid card or sticker), and whether the operation is idempotent. The automatic column-finding is helpful but insufficient for full contextual completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all three parameters. The description adds no additional meaning about parameters beyond what the schema provides, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb 'Add' and resource 'sticker (an emoji) to a card', which is clear and distinguishable from the sibling remove_sticker. It does not explicitly contrast with remove_sticker, but the action is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the action 'Add a sticker to a card', but there is no explicit guidance on when to use this tool versus alternatives like add_comment or when not to use it. An agent must infer the context from the verb and resource.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and does reasonably well: it discloses that assignment is additive ('adds to existing assignees without duplicates') and documents the 'agent:<identifier>' convention for column agents. It does not mention required permissions, what happens if the board/card does not exist, or the response, so it is not fully transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loaded with the core action, then behavior, then the agent-format detail. No filler; every sentence carries information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple three-parameter mutation with no output schema, the description covers the action, the additive/dedup behavior, and the agent identifier convention, which is most of what an agent needs. Missing elements are permission requirements and failure behavior, minor for a tool of this complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents cardId, boardId, and assignee. The description's mention of 'agent:<identifier>' mirrors the schema's assignee description, adding no new semantics beyond the structured field. Baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource: 'Assign a user or agent to a card.' An agent can immediately distinguish this from unassign_card or update_card. It does not explicitly name the sibling it contrasts with, so it stops short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied by the verb; there is no statement of when to use this versus unassign_card or update_card, no prerequisites, and no exclusions. The additive note hints at context but is behavioral, not routing guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It does disclose useful behavior beyond structured fields: the ai-software-development template provisions default agents, ownership is set to the caller, and the return contains column and agent identifiers. However, it omits permission/auth requirements, name-uniqueness constraints, and any failure modes for a persistent-state-creating operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the verb and the resource. The parenthetical template detail is long but earns its place by explaining a non-obvious side effect (agent provisioning); no filler sentences.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no annotations and no output schema, the description compensates by naming what the return value contains (board, column, and agent identifiers) and what the templates create. What is missing is operational context such as required permissions or how ownership interacts with the other board tools.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline would be 3, but the description adds real meaning for the template parameter by enumerating the columns each option produces (Todo/In Progress/Done vs. Inbox/Triage/In Progress/Code Review/Testing/Done plus default agents). That is more than the schema's terse "The layout to start from. Defaults to blank."

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource (create a board) with an ownership qualifier ("you own") and explicitly names the two template variants. An agent can distinguish this from list_boards, get_board, and update_board_context without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the creation semantics and the template enumeration, but there is no explicit when-to-use statement, no named alternative, and no prerequisites (e.g., permissions, whether a repository is required for the ai-software-development template). Adequate but leaves selection context to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It says "Create a new card", which implies mutation, but gives no information about side effects (e.g., position in column, notifications, return value), permissions, or irreversibility. For a mutation tool with zero annotation coverage, this is a significant gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with zero waste. It efficiently states the action and scope without unnecessary elaboration.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given a mutation tool with no annotations, no output schema, and three required parameters, the description is insufficient. It does not explain side effects, permissions, or what happens on success/failure. An agent would need to make risky assumptions to invoke it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema fully documents the three required parameters. The description adds no additional parameter semantics beyond what the schema already provides. Baseline 3 is appropriate when the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ("Create") and resource ("card"), and adds the placement scope ("in a column"). It clearly distinguishes the tool from siblings like update_card, delete_card, and move_card, though it does not explicitly name a contrasting sibling. The core action is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus alternatives such as update_card or add_comment. It also omits prerequisites like required permissions, board existence, or column validation. The agent is left to infer usage from the name alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It usefully discloses a non-obvious implementation behavior — that the column is resolved automatically, so no columnId is needed — but omits the critical traits for a delete: irreversibility, undo, cascading effects, and required auth.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, zero waste, with the core action front-loaded before the supplementary scoping detail. Nothing needs to be cut.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Parameters are fully covered and there is no output schema to explain, but a destructive tool with zero annotations and no description of irreversibility or error behavior falls short of what an agent needs before invoking it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and both parameters (boardId, cardId) are self-documented. The description adds no per-parameter detail, but the auto-column note implicitly explains why no column parameter is required — a minor value-add over the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ("Delete a card") that is unambiguous and matches the tool name. The second clause adds scope (auto-locates the containing column), but nothing distinguishes it from siblings like update_card or move_card beyond the obvious verb.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use guidance, no mention of prerequisites or permissions, and no alternatives offered (e.g., archive vs delete). The agent must infer that this is the destructive path from the verb alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and does well: it discloses the guard condition that blocks deletion and the cascading, permanent destruction of cards. It omits permission/auth requirements and whether the column removal itself is recoverable, which keeps it short of a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, zero filler, with the refusal condition and the destructive opt-in front-loaded in that order. Every clause earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive tool with no annotations and no output schema, the description covers the critical hazards an agent must know before calling: the precondition and the permanent cascade. Missing only peripheral details like permissions or reversibility of the column itself.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning to deleteCards beyond the schema text by stressing the deletion is permanent and tied to the refusal behavior. boardId/columnId gain nothing, so not a 5.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ("Delete a column") that is immediately distinguishable from sibling delete_card and the rename/reorder column tools. No explicit sibling routing, but the action and target are unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives a meaningful precondition (refused while the column has cards) and the escape hatch (deleteCards), which is real usage guidance. It does not, however, name alternatives or say when to prefer this over e.g. moving cards out first, so guidance is implied rather than explicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It discloses one useful behavioral trait — that images are returned visually viewable — but says nothing about non-image attachments, size limits, permissions, or failure behavior. A read-only nature is implied by 'Get' but never confirmed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, no filler, with the action front-loaded and the parameter-source hint immediately after. Every clause earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema and no annotations, so the description is the only source of return-value information. It covers the image case but leaves unclear what happens with non-image files, which is a meaningful gap for an attachment-retrieval tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description goes beyond the schema by tying fileId to its origin in get_board's attachment list, which is genuinely useful for correct invocation. boardId and cardId semantics remain schema-only.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Get a file attached to a card') and distinguishes itself from the sibling get_board by naming it as the source of the fileId. An agent can immediately tell this retrieves a single attachment rather than board or card data.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly tells the agent where the required fileId comes from ('the card's attachments in get_board'), which is the key prerequisite for calling it. It gives clear usage context but no exclusions or error-case guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full disclosure burden. 'Get' implies a read operation and it usefully states the returned composition, but it says nothing about permissions, behavior for a nonexistent or unauthorized boardId, or whether the fetch is expensive/rate-limited.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence with no filler; the resource and its payload are stated immediately.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description is responsible for explaining return values. It lists the top-level contents but leaves 'context' and 'agents' undefined and says nothing about nesting, size, or error cases, so it is only partially complete for a no-output-schema tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% for the single boardId parameter, so the schema already documents the input. The description adds no format, source, or lookup detail beyond what the schema provides, which is the expected baseline of 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb ('Get') and resource ('a full board'), and enumerates the returned contents (columns, cards, context, agents), which distinguishes it from list_boards. However, it never names list_boards as the shallow alternative, so sibling differentiation is left implicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit guidance on when to use this tool versus list_boards or the card-level siblings. The word 'full' hints that this is the detailed retrieval path, but the agent must infer that on its own.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden, and it discloses the returned payload in unusual detail (columns, agents, per-card first line, assignees, stickers, work, comment count, last comment author, agentId, time) plus the deliberate exclusion of comment bodies. It does not state the read-only/no-side-effect profile or any auth or rate-limit constraints, which is the remaining gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, no filler, and the scoping/alternative information is placed last where it belongs. The field enumeration is dense but earns its place because there is no output schema to carry it.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a single-parameter read tool with no output schema, the description covers both the return shape and the routing to alternatives, which is what an agent needs. Minor omissions (pagination, size limits, whether it is strictly read-only) keep it short of a 5.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and there is only one parameter (boardId), so the schema already documents the input fully. The description adds no syntax, format, or constraint detail about boardId, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Get a compact board') and enumerates exactly what the compact form contains, so the agent knows this is a trimmed board view. It also names the siblings it is not (get_board, get_comments), letting an agent distinguish it without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states what this tool does not return ('No comment bodies') and routes the agent to the alternatives (get_comments, get_board) for full content. The only gap is that the inverse condition — when to prefer the summary over get_board — is left implicit rather than stated as a rule.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. 'Get' implies a read, but it says nothing about ordering, pagination, result limits, permissions, or what happens for a card with no comments.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence with no filler, well-sized for a simple lookup. It is perhaps overly terse given the gaps, but nothing is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple 2-parameter read tool with a fully documented schema and no output schema, the description is minimally adequate. It still omits return shape detail (order, count, empty-case behavior) that an agent would benefit from knowing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so both boardId and cardId are documented in the schema, making 3 the baseline. The phrase 'on a card' reinforces cardId but says nothing about boardId's role or any format constraints.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clear verb+resource: 'Get all comments on a card' tells the agent exactly what is retrieved and scopes it to a card. It doesn't explicitly contrast with sibling add_comment, but the read-vs-write distinction is obvious from the verb.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives such as add_comment, nor any prerequisites (e.g. needing a valid board/card). The agent must infer usage entirely from the name.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden but only states that it lists boards with a summary. It doesn't disclose whether it requires authentication, returns all boards or paginated results, or what the 'column summary' contains beyond a vague phrase.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single efficient sentence that front-loads the action and resource. There is no wasted wording, though the phrase 'name and column summary' could be slightly more precise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter list tool with no annotations and no output schema, the description is too thin. It should at least confirm the return shape or note that it returns all boards without pagination, since no structured field fills that gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes zero parameters, so per the rules the baseline is 4. No schema or description param details are needed, and the description appropriately contains no parameter discussion.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states a specific verb ('List') and resource ('all boards'), and adds scope detail ('name and column summary'). It is distinguishable from sibling get_board by implying a bulk listing, though it doesn't explicitly contrast with it.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use guidance, no alternatives mentioned, and no exclusions. The description solely states what the tool returns, leaving the agent to infer when it is appropriate relative to get_board or other tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. 'Automatically finds the source column' is a genuine behavioral disclosure, but for a mutation tool it omits permissions/auth requirements, what happens to the card's position ordering, failure modes, and whether the move is reversible. One useful trait among several required.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short, front-loaded sentences with no filler; the primary action leads and the auto-detection note follows. Nothing is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With a fully documented schema, no output schema, and four simple flat parameters, the description is minimally sufficient for invocation. However, as a mutation with no annotations and no return-value contract, it leaves error behavior and side effects unspecified.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all four parameters (boardId, cardId, toColumnId, index) are already documented in the schema, including index's 0-based/default-to-end behavior. The description adds no parameter-level detail beyond that, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb and resource ('Move a card') plus the target scope ('to a different column'), so the action is unambiguous and clearly distinct from siblings like create_card or update_card. It stops short of naming or contrasting with any sibling, which keeps it from a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no statement of when to use this tool versus update_card or assign_card, nor any prerequisites (e.g., card must exist, board/column must belong to the same board). The only inferable guidance is the implied fact that the caller need not supply a source column.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden, and it does disclose one genuinely non-obvious trait: when a sticker appears multiple times, only one instance is removed. However, it says nothing about what happens if the sticker is absent, whether the operation requires specific permissions, or what is returned.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, the core action front-loaded and the edge-case qualifier second. Every sentence earns its place with no padding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple mutation tool with no annotations and no output schema, the description covers the basic action and one edge case but omits the no-op/error behavior when the sticker is missing and any auth or response expectations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so cardId, boardId, and sticker are all documented in the schema. The description adds only the notion of the sticker emoji being the target; the duplicate-handling note is behavioral rather than param-level. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (remove) and resource (sticker) plus its scope (from a card), which clearly distinguishes it from the sibling add_sticker. It stops short of explicitly naming the inverse tool, but the intent is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this versus alternatives such as add_sticker, nor any preconditions (e.g., whether the sticker must exist on the card). The usage context is only implied by the tool name.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden, yet it discloses nothing about permissions required, whether the rename affects existing card references, or reversibility. The word 'Rename' implies a mutation, but that is the only behavioral signal present.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two words are certainly front-loaded and waste-free, but this is under-specification rather than tight writing; there is no structure to speak of and nothing beyond the name is communicated.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a three-required-parameter mutation tool with no annotations and no output schema, the definition is not complete enough – an agent gets no guidance on side effects, validation, or what a successful rename returns.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% – boardId, columnId, and name are all documented in the schema with clear one-line meanings. The description adds no parameter context beyond what the schema provides, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource ('Rename a column'), so an agent immediately knows it mutates an existing column's name. However, it offers no differentiation from adjacent siblings such as reorder_column, delete_column, or update_column_agents, which matters in a 20-tool toolset.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no statement of when to use this tool versus alternatives, no prerequisites, and no scope constraints. An agent must infer everything from the name alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It does disclose one meaningful side effect: cards are preserved during the move ("keeping its cards"), which distinguishes it from a destructive delete/recreate. However, it says nothing about permissions, whether other columns' indices shift, out-of-range index behavior, or reversibility.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single tight sentence with the verb, resource, destination, and the key side-effect clause front-loaded. No filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, so return values need not be described, but with zero annotations on a mutation tool the description should address index-shifting of neighbors and permission expectations. It covers only the cards-preservation behavior, leaving the reindexing semantics an agent must reason about unstated.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the schema already documents index as the 0-based new position plus the two identifiers. The description adds no format or semantics beyond that, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (move) and resource (column) plus the target state (new position on its board), which cleanly separates it from rename_column, delete_column, and add_column in the sibling set. It stops short of naming those siblings explicitly, so it is clear but not fully differentiated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance, no prerequisite (e.g. the column must already exist on the boardId), and no mention of alternatives such as delete_column plus add_column. The usage must be inferred entirely from the verb.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full disclosure burden. It does add useful scope information ('across all boards'), and read-only behavior is self-evident from 'Search', but it says nothing about result limits, pagination, case sensitivity, or whether archived/closed cards are included.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

One short sentence with the scope (across all boards) and the matching mode (text content) front-loaded. Nothing is padded and nothing wastes the agent's attention.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a single-parameter, read-only lookup this is roughly adequate, but with no output schema and no annotations the description should say more about what comes back (card list, IDs, ordering) and whether results are bounded. As written, an agent can call it but cannot predict the response.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the single 'query' parameter is already documented, making 3 the baseline. The phrase 'by text content' adds a small amount of meaning about what the query matches, but no syntax, length, or format guidance is given.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb (Search), resource (cards), scope (across all boards), and matching mechanism (text content). It is unambiguous and, since no other sibling tool performs search, no alternative needs to be named to tell it apart from assign_card, move_card, update_card, and the rest.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit when-to-use or when-not-to-use guidance, nor are any prerequisites or alternatives mentioned. The 'across all boards' phrase hints at the tool's breadth, but the agent must infer that this is the lookup tool to reach for when a card's location is unknown.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full behavioral burden, and it does disclose the key non-obvious trait: fields left out are kept and new commits are appended rather than replacing the existing set. It stops short of covering permissions, error behavior, or reversibility, so it is strong but not complete for a mutation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, no filler. The inventory of recordable fields comes first and the merge rule follows, so the most decision-relevant information is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 7-parameter mutation tool with no annotations, the description covers the essential behavioral gap (merge semantics). It does not describe what the call returns or what happens on failure, and with no output schema present the agent gets no substitute for that, leaving a modest gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so every parameter is already documented in the schema and the baseline is 3. The description only reinforces the commit parameter by clarifying that commits are additive, adding marginal value without introducing new format or syntax details.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource: recording development-work metadata (repository path, branch, commits, push state, PR link) against a card. That scoping clearly separates it from card-content tools like update_card or assign_card, though it never names an alternative explicitly, so sibling differentiation is implicit rather than stated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The merge sentence implies this is a partial-update tool you can call repeatedly as work progresses, which is useful usage context. However, there is no explicit guidance on when to call it versus update_card, nor any stated preconditions beyond the schema note that branch is required the first time.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full behavioral burden. It does not specify whether this is reversible, what permissions are required, what happens if the assignee isn't currently assigned, or what the response looks like. A single sentence is insufficient for a mutation tool with zero annotation coverage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, front-loaded sentence with zero waste. Every word earns its place, and the purpose is immediately clear.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutation tool with no annotations, no output schema, and multiple required identifiers, the description is too thin. It omits permission requirements, reversibility, error conditions (e.g., assignee not assigned), and the relationship to the assign_card sibling, leaving the agent under-informed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all three parameters are documented in the schema, including the special 'agent:<identifier>' syntax for the assignee. The description adds no parameter-specific information beyond what the schema already provides, making 3 the correct baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('Remove') and resource ('a user or agent from a card'), clearly distinguishing it from the assign_card sibling via the opposite operation. However, it does not explicitly name the sibling tool, so an agent must infer the relationship from the name.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Implied usage: the description names the operation (removing an assignee) but gives no explicit when-to-use guidance, alternatives, or prerequisites, such as permission requirements or whether the card must be currently assigned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full behavioral burden, and it does disclose one important trait: omitted fields are left unchanged (PATCH semantics rather than replace). It does not say whether supplying 'context' replaces the entire existing markdown, what permissions are required, or what the response looks like.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, front-loaded with the mutation target and followed by the partial-update caveat. Nothing is redundant or padded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple three-parameter mutation with no annotations and no output schema, the description covers the essential partial-update semantics but omits whether writes overwrite existing values, permission requirements, and confirmation/return behavior. Adequate but with clear gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents boardId, context (markdown), and repository (Git URL) in detail. The description adds only the 'and/or' optionality note, which is largely inferable from the schema's non-required fields, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Set') and resource ('a board's project context ... and/or repository URL'), so an agent immediately knows what the tool mutates. It does not need to distinguish itself from siblings, since no other listed tool touches board-level context.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: the wording makes clear it is for writing board context/repository, but there is no explicit when-to-use statement, no prerequisites, and no named alternative (none exists among the siblings). 'Omitted fields are left unchanged' hints at partial-update use but reads as behavior, not guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full behavioral burden, and it does add one genuinely useful trait: the column containing the card is resolved automatically, explaining why no column parameter is required. It says nothing about permissions, reversibility, or behavior when the card/board does not exist.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, zero filler, and the core action is front-loaded before the auto-resolution note.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutation tool with no annotations and no output schema, the description covers the action and the auto-resolution behavior but omits failure modes, permissions, and return/confirmation behavior. Adequate but with clear gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all three parameters are already documented in the schema, giving a baseline of 3. The description adds the meaningful implication that text is the only mutable field and that column is auto-derived, but no format or constraint details.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ("Update card text"), which cleanly separates it from siblings like move_card, delete_card, and create_card. It does not, however, explicitly name those alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no statement of when to use this versus alternatives such as move_card or assign_card, and no prerequisites. Usage is only implied by the word "Update".

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and discloses the critical behavioral trait: the list fully replaces existing agents (effectively destructive), and keeping identifiers preserves assignments/comments linkage. It omits permission/scope requirements, but covers the highest-risk behavior well.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, each earning its place: purpose, replacement behavior, and the identifier-preservation caveat. Front-loaded and free of filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 3-param mutation tool with no annotations and no output schema, the description covers the operation, its destructive nature, and the correct invocation workflow. Only minor omissions (auth requirements, the max-10 limit also present in schema) remain.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds real semantic meaning beyond the schema: that the array is a wholesale replacement and that the identifier field ties agents to existing assignments and comments. This goes beyond field-level documentation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Set the agents for a column') and immediately clarifies the replacement semantics. It doesn't explicitly differentiate itself from the nearest sibling (update_board_context), but the operation is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear workflow guidance: to change one agent, fetch the list from get_board, edit it, and resend the whole list. It names a sibling tool and the condition that selects it. No explicit exclusions or error conditions are given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.