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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered without description help. The description adds the two-step read pattern ('Pass an id to fetch') and the returned fields, which is real added context, but says nothing about result limits, ranking, or the maxLength-300 query constraint's consequences.

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?

Two short sentences with the format claim front-loaded, so there is little waste. But the wording is compressed to the point of obscurity ('in the shape ChatGPT's deep research and company knowledge use') and the dangling 'Pass an id to fetch' sentence confuses rather than clarifies.

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 an output schema present and one fully documented parameter, the description only needs to convey scope, output flavor, and the follow-up path, which it does. The remaining gap is that the search domain (free credit programs) is only inferable from the title, not the description body.

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% with a single documented 'query' parameter ('What the person wants, in plain words or provider names'), so the baseline is 3. The description's 'Pass an id to fetch' does not map to any parameter in this schema and could be misread as an input, so it adds ambiguity rather than meaning.

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 names the operation as an equivalent of search_credits and states its output shape (ids, titles, links) in a ChatGPT deep-research form, which distinguishes it from siblings like search_offers. It never plainly says *what* is being searched (free credit programs), leaning on the title to supply that, and the tool name 'search' is generic on its own.

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 routes the agent explicitly: use search_credits instead when you need eligibility or no-card filters, implicitly reserving this tool for ChatGPT-format/deep-research consumption. The phrase 'Other apps' is loose and never states a firm when-not condition for this tool, so it stops short of a 5.

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