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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety is covered; the description adds genuinely new behavior: results are computed from the transition log and a candidate rejected in March then hired in May still counts as exactly one rejection. That deduplication/counting rule materially changes how an agent should read the numbers. It stops short of describing the output shape or refresh/latency characteristics.

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 dense sentences, front-loaded with the purpose ('WHY candidacies ended') before grouping dimensions and then filters. The caps-lock emphasis (WHY, INITIATOR) is a little shouty but highlights the key distinctions; the counting-rule aside earns its place. Slightly compact to the point of strain, but no dead sentences.

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-required-parameter report with no output schema, the description covers what is grouped (reason, initiator, exit stage), what the filters mean, and the counting semantics. Remaining gaps are minor: date format, whether output includes totals/percentages, and any row limits or pagination.

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 0%, so the description carries the full burden and largely does: it names period (since/until), vacancy_id, source_id, location_id and canonical_stage as optional filters, and critically disambiguates canonical_stage as 'the stage they left FROM'. The only shortfall is that the date format for since/until is still unspecified.

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+resource: an aggregate report of 'WHY candidacies ended' broken down by typed reason, initiator, and exit stage. That is concrete enough to distinguish it from funnel/cohort siblings in spirit, but the description never names or contrasts a sibling (e.g. hr_funnel_report, hr_list_rejection_reasons), so the agent gets no explicit routing signal.

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: 'WHY candidacies ended' tells the agent the analytical question this answers, and the initiator interpretation hint ('company-initiated says the filters are wrong; candidate-initiated says the offer is') offers interpretive context. There is no explicit when-to-use, when-not-to-use, or alternative-tool guidance, and no prerequisites are mentioned.

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