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

Annotations only cover read-only and idempotent; the description goes well beyond by disclosing the ambiguity contract (returns `candidates` instead of guessing, and the agent should ask which person), the `not_captured` blind-spot list, and an instruction to repeat those limits when reporting someone as quiet. That is exactly the operational context an agent needs to avoid a wrong answer.

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?

Front-loaded with the purpose and the question it answers, then layered with interpretation and caveats; each paragraph carries distinct value. It is on the long side and repeats the ambiguity handling already stated in the `person` schema, which keeps it from a 5.

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?

An output schema exists, so return-shape explanation is not required, yet the description usefully tells the agent which field to lead with (`headline`) and what `candidates` and `not_captured` mean in practice. Combined with annotations, there is nothing an agent needs in order to call and correctly present this tool that 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 the schema already explains `days` (default 56, clamped 7–84), `person` formats and the optional `repository` slug. The description restates the name/login formats and the ambiguity-to-candidates behavior, which duplicates the schema rather than extending it. 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 — what one person has been doing in a recent window — and enumerates exactly what is returned: PRs opened/merged, reviews given, deploys triggered, plus weekly rollup, busiest days and longest quiet run. The line 'three counts read together rather than one in isolation' distinguishes it from the single-metric siblings like get-created-pull-requests-tool and get-deployments-by-person-tool without needing to open 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?

Gives concrete triggering questions ('is Dave still shipping?', 'what has Sam been working on?') and explicit interpretation guidance — lead with `headline`, don't read a PR count alone. It stops short of naming sibling tools as alternatives, so the routing against get-agent-activity-tool or get-my-insights-tool is implied rather than stated.

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