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

Annotations already establish read-only, idempotent, closed-world and non-destructive, and the description goes well beyond them: dedup rules ('each person once per stage; corrections and repeats never count twice'), the crucial 'waiting is not the same as zero' distinction, null rates when the denominator is empty, decline attribution, and approximation caveats for roles saved before outcomes existed. The only shortfall is that the shape of the returned object is described piecemeal rather than as a coherent structure.

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 purpose is front-loaded in the first clause and almost every clause carries real information (definitions, caveats, null handling). It is packed into one long sentence with heavy parentheticals, which makes it dense to parse and slightly buries the operation-level summary.

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 must explain what comes back, and it does so stage-by-stage: reached, waiting, conversions with denominators, declines, interview conversion, time-to-first-shortlist, plus the `lines` narrative and the untracked case. What is missing is an explicit statement of the top-level response structure, but the substance an agent needs to interpret results is present.

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 parameter with 100% schema description coverage ('From list_roles or create_role'), and the description adds no additional meaning about role_id. Baseline 3 is appropriate when the schema fully carries the parameter 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?

The opening clause names the resource and the exact stage set (reviewed, shortlisted, contacted, replied, interview, offer, hired), so an agent can tell this is the computed funnel report for a role rather than raw outcome retrieval (get_outcomes) or a shortlist listing (get_shortlist). It never names a sibling explicitly, and the verb is only implied by 'How a role's people moved through', 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: the description makes clear this is analytics over recorded outcomes for one role, and 'tracked false: nobody has recorded outcomes yet' hints at how to read an empty result. There is no explicit when-to-use versus get_outcomes/get_shortlist/get_role, and no prerequisite or exclusion guidance.

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