collect_vacancy_resumes

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

With no annotations, the description carries the full burden and does well: it discloses the gated budget, the bound via max/max_wait_ms, that it writes raw JSON + manifest/csv under out_dir, that truncation returns an id-based cursor with remaining, that cursor reuse is safe when new responses arrive, and that HH_ACCESS_TOKEN is required. Remaining gaps (overwrite behavior of out_dir, rate-limit specifics, captcha handling) prevent a 5.

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?

A single dense paragraph that front-loads the core action (walk funnel, fetch, write) before the bounds and cursor semantics. Every clause carries information. It is tightly packed rather than wasteful, though the run-on structure could be broken for readability.

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 9-parameter mutation/export tool with no annotations and no output schema, the description covers what the tool does, where it writes, the gating/bounding behavior, and the return cursor contract. The absence of an output schema is offset by the described cursor/remaining contract. Only captcha and file-overwrite semantics are unaddressed.

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 89%, so the schema already documents nearly every parameter, including defaults for max, max_wait_ms, collection, and out_dir. The description adds only marginal context (HH_EXPORT_DIR default, cursor safety across calls, topic_id for each resume) and does not compensate for or extend the outstanding parameter. Baseline 3 is appropriate.

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+scope: walk a vacancy funnel (collection/sub_collection), fetch each resume, and write exports to disk. This is clearly distinguishable from sibling reads like get_resumes and list_applications. It stops short of naming a specific sibling as the alternative, so it doesn't quite reach 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?

Gives one explicit routing cue — 'Prefer this over spawning subagents' — and clarifies that the cursor is safe across calls with fresh responses. However, it never says when to use this instead of search_resumes, get_resumes, or list_applications, which are the closest siblings. Usage is implied rather than contrasted with tool alternatives.

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