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

Beyond the readOnlyHint/destructiveHint annotations, the description discloses that results come from hybrid vector search matching against profiles, facts, and visual style, and that it 'can return lookalike or topical matches' and 'is allowed to miss an exact username.' It also states the return shape (ranked list with specific fields) and that flat follower/engagement/verified fields should be used to constrain numeric criteria, adding genuine behavioral insight.

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?

Although substantial, every section earns its place: a clear first-line summary, explicit usage boundaries, named alternative tools, illustrative examples, return-value summary, and filter guidance. The structure with short paragraphs and examples makes it easy to scan despite its length.

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 tool's complexity (9 parameters, multiple modes, rich sibling context), the description is remarkably complete. It covers purpose, usage timing, exclusions, alternatives, behavioral caveats, return semantics, and parameter usage—all while relying on the output schema for exact return format details.

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 input schema already has 100% description coverage for parameters, so the baseline is 3. The description adds value by warning that exact handles/usernames should not be passed in the query and by advising to use the flat follower, engagement-rate, and verified fields for numeric constraints—semantics not fully obvious from the schema alone.

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 opens with 'Semantic discovery search for influencers/content creators using natural-language queries,' which names the specific verb, resource, and mechanism. It clearly differentiates from siblings by explicitly stating this is not for exact handles/usernames and directs those cases to get_profile, search_creators, or lookup_profiles.

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 provides explicit when-to-use ('only when the user asks to discover creators by topic, audience, geography, niche, content style, or campaign criteria') and when-not-to-use scenarios, with concrete examples for both. It names specific alternative tools (get_profile, search_creators, lookup_profiles, find_lookalike_creators, match_creators) and explains when each alternative is appropriate.

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