Search projects

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

Annotations already cover read-only, open-world and idempotent, yet the description still adds substantial behavior: results are newest-first, 'times are UTC', next_cursor is null when exhausted, no matches exist, and one call scans at most 200 newest projects with 'since', which explains the key trap (a short page that still has a next_cursor).

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 what it returns and its ordering, then filters, then pagination — a sensible order. It loses a point for redundancy: 'newest first' appears in both the first and second sentences, and the opening two sentences retread the same ground.

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 carries the return-value burden and does it: budget type and currency, category, proposal count and brief start, plus a full pagination contract. Nothing an agent needs in order to page or poll correctly is missing.

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 100%, so baseline is 3, but the description genuinely extends it: 'cursor' is tied to next_cursor from the previous call, 'since' is framed as the polling watermark, and 'limit' is qualified by the scan cap. Some of the field talk (budget.type, freelancer_country) describes return values rather than parameters, which reads as slightly off-register but is not misleading given there is no output schema.

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?

Names a specific verb and resource ('open projects buyers posted', 'newest first') and immediately scopes it against the Jobs page search. The description of returned fields plus the explicit handoff to get_project for the full brief lets an agent distinguish it from search_freelancers and search_offers without opening a 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 concrete usage context: poll with 'since' to read only new postings, and use get_project when the full brief is needed. It doesn't explicitly rule out search_offers or search_freelancers, but the resource distinction is clear enough that no agent would confuse them.

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