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

Annotations already establish readOnlyHint, idempotentHint, and destructiveHint, covering the safety profile. The description adds meaningful context beyond the annotations: it indicates the call is 'Cheap' (a performance characteristic) and 'Requires a Pro or trial workspace' (an access constraint). It does not contradict any annotation, and the added context helps an agent judge whether and under what conditions to invoke it.

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 with no filler: the first states what the tool returns, the second explains its relationship to a sibling and gives a usage directive, and the third states the access requirement. The key information is front-loaded, and every sentence earns its place. This is a model of concise tool documentation.

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 one-parameter read-only tool, the description is complete: it names the returned fields, points to list_attention_cards for the underlying definitions, explains why to call it first, and notes the workspace requirement. The absence of an output schema is acceptable because the description enumerates exactly what the response contains. An agent has all the information needed to decide whether to call this tool and how 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?

The schema has 100% coverage on the single required parameter project_id, fully describing it as the unique identifier of the project. The description does not add extra parameter-level detail, but with full schema coverage the baseline of 3 is appropriate. The description's mention of the specific output fields partially clarifies what the project_id will be used for, but no additional semantics are strictly needed.

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 the tool's purpose: returning counts of cards needing attention on a project's kanban board. It enumerates the exact fields returned (overdue_cards_count, blocking_cards_count, stuck_cards_count) and differentiates from the sibling list_attention_cards by noting that sibling returns the cards behind each count. This gives an agent a precise understanding of what the tool does and how it differs from a nearby alternative.

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 says 'call this first to decide whether a deeper look is worth it', which is direct guidance on when to use it. It also contrasts with list_attention_cards ('returns the cards behind each count'), so an agent knows to use that sibling when it needs the actual cards rather than just counts. This is exactly the kind of explicit usage routing expected.

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