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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=false), and the description adds non-obvious behavior: result ordering, the fact that confidential fields come back as "***" rather than null so redaction is distinguishable from an empty value, and that redaction is uniform across every surface. That redaction contract is exactly the kind of context an agent cannot get from the schema. It does not disclose pagination defaults or result-size behavior.

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 definition is front-loaded with purpose, then filters, then return shape, then the redaction caveat — a sensible order with little filler. The final sentence about asking the workspace owner is useful but slightly padded by the 'every surface redacts identically' clause, which repeats the redaction point already made.

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 and zero schema coverage, the description does the work of explaining what each returned item carries (person, vacancy, current stage, channel, exit reason) and how redaction appears, which is what an agent needs to interpret results. The gap is pagination: with 8 params including limit/offset and no stated defaults or caps, an agent cannot tell how much data one call returns.

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 must carry the load, and it defines six of the eight parameters with real meaning beyond the field names: canonical_stage as closed funnel codes, source_id as channel, location_id as the vacancy's shop/office, and is_terminal with the concrete reading 'false = still moving'. limit and offset are never mentioned, leaving the pagination parameters undocumented in both places.

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 first sentence states a specific verb and resource ('List candidacies (applications) in the hiring funnel') plus the ordering ('newest first'), which lets an agent recognize this as the broad listing surface. It stops short of naming how it differs from the specialized siblings (e.g. hr_stuck_applications), so differentiation is implied by 'in the hiring funnel' rather than explicit.

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 through the filter inventory and the note that a closed application carries an exit reason, so an agent can infer this is the general-purpose browse tool. There is no explicit when-to-use/when-not guidance against alternatives such as hr_stuck_applications or hr_list_submissions. The one genuinely directive sentence — ask the workspace owner for the right HR role instead of trying another tool — is about redaction, not tool selection.

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