McpStamp Kanban Board

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

With no output schema, the description carries the return-shape burden well: it says the board is rendered column by column with tasks, estimate, actual and overdue counts, then board totals and remaining open estimate, plus the default selection rule. The annotations add little (readOnlyHint is false, destructiveHint false), so this output-level disclosure is the main behavioural value, though nothing is said about error behaviour or empty boards.

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 resource and its output shape, followed by the default and the alternative-tool pointer. Every clause carries information; nothing is 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 single-parameter, no-output-schema read tool this is nearly complete: it explains what is displayed, in what order, and how the board is chosen when the parameter is omitted. Only edge-case behaviour (unknown project, empty board) is left 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?

There is a single optional parameter with 100% schema description coverage, and the description only restates the default ("your busiest one") already present in the schema. Baseline 3 is appropriate since it adds no new format, matching, or ID semantics 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?

"Show one board column by column" names a specific verb and resource and immediately enumerates the content returned (tasks, estimate, actual, overdue count per column, then totals and open estimate). It also distinguishes itself from project_list, so an agent can pick between the two without opening either 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?

"Use project_list for every board" explicitly routes the agent to the sibling that covers the multi-board case, and "Defaults to your busiest board" clarifies the no-argument behaviour. It stops short of stating any precondition (e.g. what happens with zero boards or an unknown project), so it is clear but not fully closed.

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?

Beyond the annotations, the description discloses the critical side effect that tasks in a removed column move to the FIRST column. It also explains blank handling and the refusal condition after normalization, which are essential behavioral details for a column-replacement mutation.

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 definition is compact and front-loads the action, constraints, and side effect. The trailing 'Pro.' is unexplained and slightly cryptic, but the rest of the description contains no wasted wording.

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 two-parameter mutation with annotations and no output schema, the description covers the main risk: what happens to tasks in removed columns. It is nearly complete, though it leaves the meaning of 'Pro' and any success confirmation behavior 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%, so the schema already documents both parameters. The description still adds meaning beyond the schema by specifying that names must be unique and that blanks are dropped before the two-name minimum check is applied.

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: replace one board's columns, in order. It also adds the key constraints of 2 to 12 unique names, making the operation immediately distinguishable from broader sibling tools such as board or task_update.

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 replacement context is clear, and the side effect on removed-column tasks helps an agent understand when this operation is appropriate. However, it does not explicitly state when to use this versus alternatives, nor does it clarify prerequisites beyond the ambiguous trailing 'Pro.'

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?

Annotations already declare non-read-only, non-destructive, non-idempotent, closed-world. The description adds real value beyond that: the effect is scoped to 'this connection', existing data under the token is preserved, and a wrong or expired key is a no-op. It does not say whether the change is immediate or whether repeat activation is harmless, which is relevant given idempotentHint=false.

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 effect and followed by the failure guarantee and verification pointer. No filler or restated boilerplate.

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 one-parameter, no-output-schema tool with annotations covering the safety profile, this is close to complete: effect, scope, failure behavior, and a verification sibling are all covered. Only minor gaps remain (immediacy of effect, behavior when already licensed).

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 single param already documents the MCPL1 format, so the baseline is 3. The description earns an extra point by adding provenance the schema lacks: the key is issued at checkout and must be for this server or the bundle.

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 action (turn Pro on) and its scope (for this connection), plus the exact credential shape required. It also positions the sibling license_status as the verification path, so an agent can distinguish activation from status checking without opening either 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?

It states the precondition clearly: the key must be an MCPL1.<payload>.<signature> token issued at checkout for this server or the bundle, and directs verification to license_status. It stops short of explicit when-not-to-use guidance (e.g., what to do if already Pro or if the key is for a different server).

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?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds useful context beyond annotations by specifying the JSON response contents and stating 'nothing changes,' reinforcing the read-only nature of the call.

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 dense sentences cover output, purpose, usage context, and side-effect guarantee. Every sentence earns its place and the most important 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?

With no output schema, the description sufficiently describes the return value. With no parameters, annotations covering safety, and a clear use case, nothing essential is missing for an agent to invoke this tool 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?

There are zero parameters and the schema already fully documents that fact. The description explicitly says 'No arguments,' which is accurate and reinforces the schema without needing further elaboration.

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 begins with a specific verb ('Report') and a precise resource ('this endpoint's licence state for your token'), and enumerates the exact output fields: product, tier, reason, and checkout URL. This clearly distinguishes it from sibling tools like license_activate.

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 explicitly states when to call it: 'Call it to explain a free-tier refusal.' This is clear contextual guidance, though it does not name alternatives or explicitly state when not to use it.

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?

Annotations already declare this a safe, idempotent read, so the bar is lower, and the description still adds genuine behavior: results are ordered oldest-first, span all boards, and exclude completed or undated tasks. The phrase "in the task_list table" also hints at the output shape, which no annotation or output schema provides.

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 with zero padding: scope first, the as_of semantics second, then the exclusion rule. Every sentence carries information an agent needs.

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 read-only filtered list with full schema coverage and complete annotations, the description is sufficient to call it correctly. Only the returned fields are unspecified, which is minor since there is no output schema and the table reference gives a pointer.

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 both as_of and limit are already documented, including formats and the default row count. The description's "as_of measures against a day you name" only restates that, adding no syntax or interaction 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?

Specific verb and resource: "List every task whose due day is already past, across all boards, oldest first." Scope and ordering are stated up front, which separates it from the generic task_list sibling in practice, though the description never names that alternative explicitly.

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?

Implicit usage is clear from the filter definition, and exclusion rules (finished tasks and tasks with no due date never count) set a real boundary. But there is no explicit guidance on when to prefer this over task_list, task_search, or weekly_review, so the agent must infer the choice.

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?

Annotations already declare destructiveHint=true and idempotentHint=false, so the safety profile is covered. The description adds real value beyond that: the refusal behavior for non-empty boards, the side effect that task_add creates boards, and the free-tier slot accounting. It omits whether deletion is irreversible beyond the emptiness guard, which keeps it off 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, front-loaded with the action and effect, and both sentences carry information. The clause 'is refused with one named' is awkwardly compressed and slightly obscures the error semantics, which costs a point.

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 one-parameter destructive tool with full schema coverage and rich annotations, the description supplies the essential behavioral context: the emptiness precondition, the failure mode, and why boards may exist unexpectedly. Irreversibility and post-delete state are left implicit.

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 single 'project' parameter is fully documented, including the no-tasks constraint. The description reinforces that constraint but adds no new syntax, format, or enumeration detail beyond the schema, 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 ('Delete an empty board') plus the effect ('give its free-tier slot back'), which separates it cleanly from project_list and task_delete in the sibling set. An agent knows exactly what this tool does without opening the 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?

Gives a clear precondition for use (board must be empty) and an explicit when-not (a board holding open or done tasks is refused). It doesn't name the alternative path (deleting tasks first via task_delete), so the routing is implied rather than spelled out.

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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is clear. The description adds value by disclosing what data is listed and the free-tier constraints, which are not present in the structured annotations. No contradiction with annotations.

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 sentences with no filler. It front-loads the core action and output contents, then gives the routing hint. 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 zero-parameter, read-only listing tool, the description fully covers what an agent needs: what is returned, the scope ('every board'), and when to use the sibling board tool instead. The absence of an output schema is mitigated by the explicit list of returned fields.

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 has zero parameters, so the empty input schema is fully covered and there is nothing for the description to explain about parameter behavior. Baseline 4 is appropriate because the description need not compensate for any schema gaps.

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 action ('List every board') with a defined resource and enumerates the returned fields (task-id prefix, open/done counts, estimate still open, overdue count, free-tier use). It also distinguishes itself from the sibling board tool by naming that alternative, so an agent can tell them apart.

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 final sentence explicitly provides routing guidance: 'Use board for one board broken down by column.' This names the alternative tool and the condition under which it should be selected, which is exactly what an agent needs.

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?

The annotations already declare this is a non-readonly, non-destructive, non-idempotent write. Beyond that, the description discloses a real side effect (a board is auto-created on first use), a dedupe constraint (duplicate open tasks are refused, which explains the non-idempotent hint), and quota limits. It omits any mention of permissions or what happens when a quota is hit.

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?

Four short sentences, front-loaded with purpose and return values, with no filler. The final line "Free: 3 boards, 200 open." is telegraphic enough to be slightly ambiguous about what exactly is capped.

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 output schema, the description helpfully names the returned fields (id, board, column), and the eight parameters are fully documented in the schema. Missing only edge-case behavior for quota exhaustion and what the refusal error looks like for a duplicate task.

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 the schema already explains defaults for project, column, and priority, so the baseline is 3. The description only restates the project-optional behavior and adds no new semantics such as partial-name matching rules or tag normalization.

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?

"Add one task to a board and return its id, board and column" gives a specific verb (add), resource (task), scope (one), and even the shape of the result. The verb alone separates it from siblings like task_update, task_move, and task_done, so an agent can route without opening the 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?

It states key preconditions: the board is created on first use, an existing project can be passed or omitted, and an identical open task is refused. It does not explicitly name an alternative tool for editing an existing task (task_update) or searching before adding (task_search), so it falls short of full when/when-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?

Annotations already declare destructiveHint=true and idempotentHint=false, so the safety profile is known; the description still adds real context beyond them: the id is never reused, the response reports logged minutes lost, and time-tracker entries live in a separate store and are untouched. The storage-boundary note in particular prevents an agent from assuming logged time is destroyed with the task.

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 destructive action and effect, then the side effect on logged minutes and storage boundary, then the alternative. No filler or restatement of the name.

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 single-parameter tool with no output schema, everything an agent needs is present: irreversibility, id non-reuse, what the response reports, what is deliberately not affected, and the safe alternative. No material gaps 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% and the single id parameter already carries a format example (NOVA-12). The description only restates that the lookup is by id, adding no syntax or constraint detail beyond the schema, 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 with scope: 'Delete one task by id, permanently.' The permanent/non-reusable qualifier and the explicit contrast with task_done make it distinguishable from siblings such as task_done and project_delete 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 routes the agent to the alternative: 'Use task_done to keep the record.' That is a clear when-to-use-this-instead rule for the most likely confusion. It doesn't address other plausible siblings (task_update, task_move), so it stops short of full alternative coverage.

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?

Annotations already declare this is a non-read-only, non-destructive, non-idempotent mutation, and the description adds real context beyond them: the destination column resolution rule, the 'stamped' side effect, removal from task_list and open counts, and the estimate-vs-actual return payload. It does not say what happens if the task is already done or what errors occur, but coverage is well above the annotation baseline.

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 compact sentences, front-loaded with the action and state change, followed by the return value. The parenthetical column-name rule is dense but earns its place because it explains column resolution.

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 one-parameter mutation with no output schema, the description covers the state transition, side effects on listing/counts, and the return payload (estimate vs actual). Only edge-case behavior (already-finished tasks, failure modes) is missing.

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 single parameter 'id' is fully documented in the schema with an example (NOVA-12), so the description does not need to restate it and adds nothing new about it. Baseline 3 applies since schema coverage is 100%.

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 ('Mark one task finished') and pins down the resulting state change: it moves to the done column (named done, else the last) and is stamped. This also distinguishes it from the sibling task_move, which repositions tasks without completing them.

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 'mark one task finished', but there is no explicit when-to-use versus task_move, task_update, or task_delete, and no mention of preconditions such as whether the task must be open or assigned. Adequate but leaves routing to the agent's 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?

Annotations already declare this a read-only, idempotent, non-destructive, closed-world operation, so the safety profile is covered. The description usefully adds that done tasks are hidden by default and that output is sorted by due date with a total estimate appended, but it does not cover pagination beyond the default row count or whether the total estimate respects filters.

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 tight sentences, front-loaded with the returned shape, followed by scope and size defaults. The closing '200 rows default' repeats the schema's limit description and could be dropped without loss.

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 output schema, the description carries the return-value burden well by enumerating columns, sort order, and the appended total estimate. What remains thin is guidance on choosing this tool over task_search or overdue, though nothing needed to call it correctly is missing.

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, and the description's mentions of include_done and the 200-row default merely restate schema fields. It adds no new meaning about how filters combine or interact with the computed total.

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?

Specific verb and resource (list tasks) with the exact output columns, sort order, and default scope made explicit. It does not, however, distinguish itself from siblings that also return tasks such as task_search, overdue, or board.

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: it reads as the general-purpose listing tool, and the exclusion of done tasks implies an unfiltered default view. There is no explicit guidance on when to prefer task_search or overdue over this tool, which matters given three siblings that surface task collections.

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?

Annotations declare readOnly/destructive/idempotent hints, and the description usefully adds that values accumulate rather than overwrite and that negatives are corrections — behavior the annotations cannot express. It is docked for the self-contradicting bound clause: negatives are endorsed for corrections, yet 'Below zero ... is refused' is stated without clarifying whether that applies to the argument or the resulting total.

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?

Four short sentences, front-loaded with the action and the additive rule, with no filler. The closing sentence ('This counter is the board's own') is cryptic and does not obviously earn 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 two-parameter mutation with full schema coverage and annotations, the description covers purpose and additive/corrective semantics sufficiently; no output schema means return values need not be explained. The unresolved zero-boundary ambiguity is the main 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 coverage is 100%, so baseline is 3; the description does add real meaning by explaining that minutes accumulate and that negative values are corrections. However, 'Below zero ... is refused' conflicts with the schema's documented minimum of -100000, muddying rather than sharpening the parameter's semantics.

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: adding 'real minutes worked to one task' for estimate-vs-actual comparison. An agent can tell it apart from generic task_update, though it never names or contrasts with the sibling that also records time (task_start_timer).

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 'Add real minutes worked' and the estimate/actual rationale, but there is no explicit when-to-use guidance, no prerequisites (does the task need to exist, must it be started?), and no mention of task_start_timer as the alternative for running timers.

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?

Annotations cover safety (not destructive, not idempotent, closed world), and the description goes beyond them by disclosing validation-failure behavior and two non-obvious side effects: entering 'done' stamps completion and leaving it clears the stamp. That clearing is the only tension with destructiveHint=false, but it is a timestamp reset rather than resource loss, so it is not a contradiction.

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 action and scope, then error behavior, then side effects. Every sentence carries information an agent could not get from the schema or annotations.

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 two-parameter mutation with no output schema, the description covers the action, validation failure mode, side effects, and return content (old and new column). Only permission requirements and concurrent-modification behavior are unaddressed, which is a minor gap at 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 coverage is 100%, so the baseline is 3, but the description adds genuine meaning: the column must be an existing column of the task's own board, unknown values are refused with the real list, and the 'done' column carries special stamping semantics. That 'done' behavior is not expressible in the schema at all.

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), resource (one task), and destination constraint (another column of its own board), plus what it reports back. The phrase 'of its own board' implicitly bounds scope against a cross-board move and separates it from task_update and task_done without opening either 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 resource-scoped phrasing but never states when to prefer this over task_update or task_done, both of which can also change a task's state. No explicit when-not guidance or prerequisites are given.

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?

Annotations already declare readOnly, idempotent and non-destructive, so safety is covered. The description adds genuinely new behavioral context: case-insensitive plain substring, never a regex, and that finished tasks and all boards are included. It does not say anything about result ordering or how limit truncation interacts with matches, which keeps it off 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?

Three short sentences with zero filler. The matching behavior and scope are front-loaded, and the sibling routing note is placed last as a decision aid.

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 two-parameter read tool whose annotations already carry the safety profile, the description covers search semantics and alternatives well. The only omission is result shape/ordering, but with no output schema this is a minor gap rather than a blocking one.

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: it specifies that query is matched against id, title, notes and tags and that matching is a case-insensitive substring rather than a regex. The limit parameter is left entirely to the schema, which is acceptable but not additive.

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 ("Find tasks") and defines the matching fields (id, title, notes, tags) plus scope (every board, finished included). It explicitly contrasts with task_list, so an agent can distinguish it from the sibling without opening a 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?

It names the alternative explicitly — "Use task_list for structured filters" — which tells the agent exactly when to pick the other tool. Combined with the free-text matching semantics, the usage boundary is unambiguous.

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?

Annotations declare readOnlyHint=false, non-idempotent, non-destructive, closed-world, and the description is consistent with that: it says a link is recorded here, explaining why this is a write despite 'starting nothing'. It also discloses a non-obvious behavior, warning when the tracker's own project names would misfile the time. It does not say what the recording overwrites or whether it can be undone, which keeps it below 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 short sentences with the key negative constraint front-loaded, so the reader learns what the tool does not do before anything else. 'Record the link here' is slightly vague about what link and where, which is a small cost in an otherwise economical definition.

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 output schema, the description does explain the return value as arguments for timer_start, and it flags the write side effect and the misfiling warning. For a one-parameter tool this is largely sufficient, though it leaves the shape of the returned arguments and the warning payload 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?

The single parameter is fully documented in the schema (100% coverage, with an example format like NOVA-12), so the schema carries the burden. The description adds no further meaning about accepted id forms, task lookup failures, or how the id relates to the derived timer_start arguments, 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 concrete verb and result: it returns the exact arguments to pass to the external timer_start and records the link. It also explicitly negates the naive reading of the title ('It starts nothing itself'), so an agent will not mistake it for a direct timer start. It stops short of a 5 because it never names the task resource explicitly beyond the schema's 'id'.

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 rather than stated: the agent is told this produces arguments for timer_start, which suggests calling it before that external call, and the misfiling warning hints at a validation purpose. There are no explicit when-not-to-use conditions or named alternatives among the siblings (task_log_time, task_done), so the routing guidance stays implicit.

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?

Annotations only declare the generic mutation profile (not read-only, not destructive, not idempotent, closed world). The description goes beyond them with genuinely non-obvious behavior: tags fully REPLACES the list, due accepts 'none' to clear, and project requires a pre-existing board. The return value is also disclosed ('the task's new row'). It does not mention whether failed mid-update leaves partial state, which is the main 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 tight sentences, front-loaded with the operation and the partial-update rule, followed by the three behaviors that would otherwise trip an agent up. Nothing is padded or repeated from the schema verbatim without added meaning.

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 9-parameter mutation with 44% schema coverage and no output schema, the description covers the highest-risk behaviors (list replacement, clearing, board precondition) and the return shape. It is short of complete because the remaining fields — especially whether 'column' implies a move and what priority/estimate do — are left entirely to a partially documented schema.

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 44%, so the description should carry more weight. It reinforces the three already-documented fields (tags, due, project) but adds nothing for the undocumented ones — notes, title, column, priority, estimate_minutes — leaving roughly half the parameters with no semantics anywhere. The 'only fields you pass are touched' clause does at least explain the overall patch model across all nine.

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 ('Change a task by id') and immediately scopes it as a partial update ('only the fields you pass are touched'). It implicitly separates itself from task_move/task_add by framing 'project' as moving to an 'existing' board, but it never names a sibling, so the differentiation is inferred 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 partial-update line implies when to use this over a full rewrite, and 'a board that already exists' signals a precondition for the project field. There is no explicit when-not guidance or pointer to task_move, columns_set, or task_done for the cases this tool handles awkwardly (e.g. reordering within a board).

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?

Annotations declare readOnlyHint=false, which is surprising for what reads as a reporting/aggregation operation, and the description never clarifies whether the call mutates anything — leaving the agent with no way to reconcile the two. On the positive side, the description does disclose a behavioral trait annotations cannot express: that past weeks require a Pro license, which is exactly the kind of context the schema alone would not make obvious.

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 whole definition is one dense, front-loaded sentence with no filler, and the licensing caveat is placed last where it is least disruptive. It loses a point because the metric list is slightly ambiguous — 'how many were due' versus 'how many were completed' leaves the reader guessing at the exact definitions without an output schema to check.

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 one-parameter, non-open-world aggregation tool with no output schema, the description covers enough: it enumerates the measures returned and notes the Pro gate. What is missing is the shape of the response (per-project keys, whether counts are nested with the minute estimates), which matters somewhat since no output schema exists to fall back on.

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% for the single 'week' parameter, including the ISO format example and the Pro restriction, so the description adds little parameter detail beyond what is structured. It does contribute one non-schema semantic: the result is scoped 'per project', implying multi-project output for a single week argument.

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 ('compare done against planned for one ISO week per project') and then enumerates the exact metrics it returns (due, finished, completed, estimate vs actual minutes). That metric breakdown makes it clearly distinct from siblings like 'overdue' (late-task listing) or 'board' (status view) without needing to name them.

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: an agent can infer it is for retrospective planned-vs-actual review of a week. The only explicit guidance is the monetization gate ('Any week but this one is Pro'), and there is no statement of when to prefer this over 'overdue' or 'board', nor any exclusion such as 'do not use for real-time status'.

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