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

Annotations already provide readOnlyHint=true, so the description confirming 'Read-only and free' adds safety context but does not repeat the annotation. The description further discloses the return shape ('rich results with a description snippet, trend and claim status'), which goes beyond the annotation. However, it omits pagination cursor/offset behavior despite 11 parameters including a limit. Since the output schema exists but is not shown, and the description doesn't fully cover result set limits, a 4 is appropriate – strong but not exhaustive.

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, perfectly front-loaded. Every clause serves a purpose: scope ('own ideas + marketplace'), filter dimensions, return value hint, safety declaration, and special-case usage. No filler or redundancy. This is an exemplar of efficient description writing.

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?

Given the high parameter count (11), 100% schema coverage, readOnly annotation, and the presence of an output schema, the description adequately covers the tool's behavior. It explains the core search+browse modes, what results contain, and its read-only nature. The complexity is moderate (filtering/searching) and the description addresses the key decision points an agent needs: what it returns, what filters matter, and how to use query vs. empty case. Complete for this context.

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 100%, so baseline is 3. The description adds value by explaining that 'query' matches title+description (not in schema description), and clarifies the filter-only fallback. It also contextualizes the VC score range as a primary filter dimension. However, it doesn't add detail for all 11 params (e.g., 'sortBy' options, 'visibility' enum values are schema-only). This is good incremental value without being exhaustive.

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 specifies a clear verb ('Search') and resource ('ideas'), distinguishes the scope ('your own ideas and the public marketplace'), and enumerates key filter dimensions (keyword, type, VC score range, sector, claim status, visibility). It also differentiates from siblings by mentioning 'public marketplace' – no other browse/search tool does this. The 'with filters only' fallback is a helpful usage hint.

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?

Explicitly states when to use this tool (search by keyword/filters) and when not (reading results beyond snippet). Offers a special-case usage ('leave the query empty to browse with filters only'), which directly guides the agent. No sibling tool covers the intersection of own+marketplace searching, so the implicit alternative guidance is strong.

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