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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description still earns credit for domain-specific behavior beyond the annotations: the `tag:<id>` query convention and the fact that results carry typed ids intended for a follow-up `fetch` call.

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 sentences, front-loaded with the usage trigger, then the return shape, then the exclusions. No filler and no restatement of the tool name.

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?

The tool is simple (one param, annotations present, output schema available), and the description covers trigger, exclusions, query syntax, and result chaining. The remaining gap is routing against the near-duplicate `listings_search` sibling, which an agent facing 14 siblings would want resolved.

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?

With a single parameter at 100% schema coverage, baseline is 3; the description exceeds it by documenting query syntax that the schema does not (the `tag:<id>` keyword form) and implying the free-text fields the query matches.

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 resource scope explicitly: listings, apps, tags, charts, and tracked MCP URLs, plus the chaining outcome ('returns typed ids for fetch'). It does not, however, differentiate this generic 'search' from the sibling `listings_search`, which by name covers overlapping ground — an agent could reasonably pick either.

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 both a when ('use this when ... needs listings, apps, tags ... charts or tracked MCP URLs') and explicit when-nots with named alternatives ('Do not use for rankings or events; use charts_get or changes_list'). The trigger clause is oddly narrow, framed around 'ChatGPT deep research', and never mentions the `listings_search` alternative.

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