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

Annotations already cover the safety profile (readOnly, non-destructive), and the description adds substantial extra context: sub-second latency, active-listings-only scope, default newest-first ordering with sort=popular as an alternative ranking by discussion activity, the important semantics that unmarked work_mode means unstated rather than onsite, and the pagination contract (pass next_cursor back as cursor, keep all other arguments identical).

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?

Dense but front-loaded: filtering scope and speed first, sibling routing second, then per-parameter caveats and pagination. Every sentence carries a concrete behavioral or semantic fact, with no filler.

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 10-parameter, all-optional search tool with no output schema, the description covers the full calling contract an agent needs: valid input domains for the strict filters, ordering, freshness, and how to continue pagination via next_cursor.

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 80%, so the schema already documents most parameters, but the description adds genuine meaning beyond it: query is a case-insensitive substring on titles only with synonym/short-token advice, companies must be exact values from list_companies, locations must be identifiers from search_locations, and work_mode only matches explicitly marked jobs.

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 (search) and resource (aggregated job postings) with structured filters, and explicitly distinguishes itself from the sibling match_jobs by naming the exact selecting condition (one specific person's resume/skills/visa). An agent can route between search_jobs and match_jobs without opening either schema.

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 explicit when-to-use ('browse, list, count or page through postings', general hiring questions) and when-not ('to find the best postings for one specific person... use match_jobs instead'), plus practical exclusions for thin results and the exact constraints for companies/locations filters.

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