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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds meaningful behavior beyond that: results are derived from an append-only transition LOG, which explains why rejected candidates still appear in stage counts, and it discloses that 'until' is exclusive. It does not address cost/performance, result size, or whether unfiltered calls scan the entire dataset.

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 report's contents, then the log-derivation caveat, then the filters — a sensible order with no filler. The first sentence is dense and parenthesis-heavy, which slightly taxes scanning, but every clause conveys substantive 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?

With no output schema, the description takes on the burden of describing returns, and it does so thoroughly (per-stage counts, rates, median time, SLA, headline metrics). For a five-parameter read-only report with annotations covering safety, the only gaps are minor: no default time window when filters are omitted and no note on timezone or 'since' inclusivity.

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 0%, so the description must carry the parameters and it largely does: since/until are given a YYYY-MM-DD format and 'until' is explicitly exclusive, and vacancy_id/source_id/location_id are identified as scoping filters. The three ID filters are named but not otherwise explained (e.g. what a source or location represents), and no defaults are stated when omitted.

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-and-resource: it enumerates exactly what the funnel report computes per canonical stage (entered, moved on, dropped, still there, drop-off/conversion, median time in stage, SLA breaches) plus headline metrics. That is far more than a restatement of the title, and it is distinguishable from siblings like hr_stage_durations_report or hr_dropoff_reasons_report by content. It does not explicitly name a sibling it should be preferred over, keeping it just below 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?

Provides real context for when this is the right report: it is read-only and computed from the append-only transition log, so candidates who reached a stage still count after rejection — implying this is the historical/ever-reached funnel rather than current-state headcount. It also clarifies that filters are optional. No explicit exclusions or named alternatives among the many sibling reports.

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