find_similar_corpus

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

With no annotations, the description carries full responsibility for behavioral transparency. It discloses the scoring algorithm (embedding cosine + engagement bump with log10 likes), which explains how results are ranked. The wording clearly implies a read-only retrieval operation, though it doesn't explicitly state that.

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?

The description is two short sentences. The first front-loads the core purpose ('RAG retrieval'), and the second provides a concise scoring formula. Every word earns its place with no redundancy.

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 retrieval tool with no output schema and no annotations, the description adequately covers the main aspects: what it returns, how results are scored, and optional parameters. A minor gap is that it doesn't specify the structure of each returned lead magnet, but that's often understood from 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?

The schema already covers 75% of parameters with descriptions, but the description adds extra meaning: it clarifies 'k' as top-K, describes 'query' as free text, and states that 'brands' are optional. The scoring formula also explains how 'k' results are selected, going beyond the 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?

The description clearly states the tool's function: it returns the top-K lead magnets from the corpus most similar to a query. The specific verb 'retourne' and resource 'lead magnets du corpus' distinguish it from sibling tools like list_corpus (listing all) and generate_lead_magnet (creating).

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?

The description provides a clear context for usage: 'RAG retrieval' and 'most similar' imply this is for similarity-based search on the corpus. It doesn't explicitly name alternatives or exclusions, but the intended use case is evident. This qualifies as 'clear context, no exclusions'.

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