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

Annotations only declare idempotent/non-destructive; the description adds real behavioral context: retrieval is quota-limited and non-exhaustive, results must be backed by original-text evidence, an empty/unavailable result does not imply no budget or a closed deal, and the tool will not auto-contact, message, invite, or pay. This materially exceeds what the annotations convey.

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: the prerequisite tag opens, then purpose, then parameter roles, then caveats and next action. It packs prerequisites, params, non-fabrication caveats and side-effect boundaries into a couple of compact lines with no filler, though the telegraphic style approaches cryptic.

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 non-destructive, no-output-schema search tool it covers auth prerequisites, purpose, param roles, non-exhaustiveness, non-fabrication of conclusions, and explicit non-side-effects. The only missing piece is an explicit statement of which sibling to prefer for broader or differently-scoped searches.

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. It adds meaning for offering ('write your own capability') and q ('supplement restrictions') but only implies limit via the word 'limited'; its default of 5 and max of 10 are never clarified, leaving one of three parameters underspecified.

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 description states a specific verb+resource: 'find project buyers' by searching 'live public needs' relevant to a service provider's own capability. It defines the scenario (a service provider seeking demand-side customers) but never names competing siblings such as search_needs or list_needs_feed, so differentiation relies on inference.

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?

It gives a prerequisite ([login + AI authorization]), says what to put in offering vs q, and prescribes a next step ('before contacting, use get_need to verify the latest'). It omits explicit when-to-use-vs-alternative guidance against search_needs/search_my_own_words.

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