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

Annotations already declare readOnly=false, idempotent=false, destructive=false, and openWorld=true, so the safety profile is covered by structured data. The description adds nothing beyond this – it does not mention that repeated calls create duplicate comments (non-idempotent), whether the author is attributed, whether notifications fire, or what happens on an invalid task id.

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 waste. It is appropriately terse for a two-parameter tool, though that terseness is partly why usage and behavior are underspecified.

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-param mutation with full schema coverage and annotations present, the description is minimally sufficient. It omits return/payload behavior (no output schema exists) and the non-idempotent duplicate-comment caveat, both of which an agent would benefit from knowing before calling.

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 (id, text) are fully documented, including the Markdown constraint. The description only restates what the schema already says, 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?

Specific verb+resource ("Add a comment") with the format qualifier (Markdown) and target (a task). No sibling among create_task/get_task/update_task/list_* overlaps, so the distinction 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?

No guidance on when to use this versus update_task (e.g. editing an existing comment body) or any prerequisite that the task id must exist. The agent must infer all usage conditions 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?

Annotations already declare the write/non-idempotent/open-world profile, so the bar is lower. The description's most useful addition is the duplicate-label error condition, but that same constraint is already spelled out in the schema's create_missing_labels parameter; it adds no insight on failure modes for unknown assignees, permission needs, or what object 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?

One front-loaded sentence with the verb and resource first, followed by the optional field list. It is dense but every clause maps to a real parameter; a short note on the update_task boundary would have improved it further.

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 annotations covering the safety profile and a fully documented schema, the description provides enough for correct invocation. The only gap is the lack of guidance on how it relates to update_task and whether repeated calls create duplicates.

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 every parameter is already documented, including the 0-5 priority scale and due-date format. The description's mention of 'priority 0-5' and 'assignees by username' restates schema content rather than adding new meaning, 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?

A specific verb plus resource ('Create a task in a project') that is immediately distinguishable from update_task, get_task, and list_tasks. The sentence also enumerates the creatable attributes, so the agent knows the scope 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?

Creation is implied as the right operation when a new task is needed, and the label/existence constraint hints at prerequisites. However, it never explicitly contrasts with update_task (e.g., 'use update_task for existing tasks') or states whether the project must already exist.

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, so safety is covered; the description adds genuinely new behavioral detail by disclosing that only the 50 most recent comments are included and that long text is truncated. These are exactly the kind of limits an agent needs before calling, though return-shape caveats like missing-task behavior are absent.

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 sentence, front-loaded with the core action and followed by a compact parenthetical of return details. No redundant or filler text; every clause 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?

No output schema exists, so the description carries the burden of describing returns, and it does so well (fields, description text, comment authors/dates, count limit, truncation). It stops short of covering error or not-found behavior, keeping it from 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?

With a single parameter and 100% schema description coverage, the schema already documents 'id' as a task id. The description adds no syntax or format detail (e.g., how to obtain the id) 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 ('Read') and resource ('one task') and enumerates what is returned: all fields, description as text, and comments. It implicitly contrasts with list_tasks by emphasizing 'one task', but never names the sibling, so it falls short of full differentiation.

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 case is implied ('read one task'), but there is no explicit guidance on when to choose this over list_tasks or comment, and no mention of prerequisites such as needing a valid task id. Adequate but with clear gaps.

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 and openWorldHint=true, so the safety profile is covered. The description contributes one genuine behavioral fact not in the structured fields: results are capped at 100. It does not say whether that cap means truncation, pagination, or an error, and gives no ordering or completeness guarantees.

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 comes first and the returned fields and the 100-item cap follow 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?

For a zero-param read tool with no output schema, describing the returned fields is the right move and it does so. The only gap is the ambiguity around the 100-item cap — whether the agent should expect truncation or page through results.

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 the baseline is 4; the schema is empty and the description correctly makes no parameter claims. There is nothing for the description to compensate for.

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 ('List') and resource ('projects') and even enumerates the fields returned (id, title, parent project, open task count). It is clearly distinct from the task-oriented siblings, though the description never explicitly contrasts itself with 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 this is the tool for enumerating projects, but there is no statement of when to prefer it, no prerequisites, and no alternatives named. For a zero-parameter list tool the risk is low, but the guidance is absent 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?

Annotations already declare readOnlyHint and openWorldHint, so safety is covered. The description adds genuinely useful behavior beyond that: the default filter (open tasks), the sort order (priority then due date), and the result cap ('limit up to 100'), which warns the agent that output can be truncated.

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 with no filler, and the most important information (subject, default scope, ordering) comes first. Every clause carries content 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 six-parameter, fully documented read tool with no output schema, the description covers defaults, ordering, and truncation risk adequately. It falls short only on return shape and whether the limit implies no pagination, which an agent might wonder about with up to 100 results.

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 parameters are already fully documented. The description only enumerates filter names and the limit ceiling, both of which are in the schema; it adds no format or interaction detail (e.g., how search combines with other filters), 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 and resource ('List tasks') plus scope details: open by default, sorted by priority then due date. It is clearly distinguishable from get_task, create_task, and update_task by name and semantics, though it never names those siblings 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?

It implies the usage context by saying results are 'open ones by default' and that a done filter exists, which lets an agent infer how to retrieve completed tasks. However, it never states when to use this instead of get_task or how to page through large result sets, leaving routing 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?

Annotations already declare destructiveHint=true, idempotentHint=true, openWorldHint=true, and readOnlyHint=false, so the safety profile is covered. The description adds replacement/clearing semantics for description and due, but mostly repeats schema details and does not discuss permissions, side effects, or return behavior.

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 that efficiently enumerates the supported changes with no wasted wording. The most important operation is stated first.

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?

Covers most operations for a 12-parameter mutation tool, including labels, assignees, due date, and project moves. It omits create_missing_labels and the required id, but the schema and annotations fill those gaps adequately.

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 12 parameters are already documented in the schema. The description enumerates the same fields and adds little semantic detail beyond what the schema provides, making the baseline 3 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 and resource ("Change a task") and enumerates the mutable fields, making it clearly distinct from create_task, get_task, and list_tasks. An agent can identify the operation 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?

Implies use for modifying an existing task, but gives no explicit when-to-use or when-not-to-use guidance. It does not name alternatives such as create_task or get_task, nor does it state prerequisites like needing a task id.

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