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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context: it returns a match score (0-1), a good/neutral/avoid decision, and structured reasons, and it clarifies that candidates can be passed as UUIDs and/or profiles. This goes beyond annotations, though it doesn't describe sorting, pagination, or failure behavior, so it isn't a 5.

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 longer than average but well-organized: core purpose first, followed by parameter guidance, sibling disambiguation, and concrete examples. Each sentence adds value, though the example section is somewhat verbose and could be tightened without losing clarity.

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 has 4 parameters, full schema coverage, an output schema, and 13 sibling tools, the description provides sufficient context: it explains what the tool does, when to use it, how to handle different input forms, how it relates to siblings, and includes both brief and full user-intent examples. There are no significant gaps for an agent to invoke it correctly.

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 the baseline is 3. The description adds practical parameter semantics by stating that creator_ids and profiles can be used 'and/or', that intent_query is 'the brief the LLM reasons against', and that intent_context is optional extra context (target audience, brand values, prior collabs). This helps an agent compose valid inputs beyond what the schema alone conveys.

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 a specific verb+resource: 'Score how well specific creators fit a campaign brief or search intent.' It clearly distinguishes this from sibling tools by noting the tool evaluates existing candidates, whereas semantic_search_creators is for discovery and search_creators for resolving handles.

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 guidance: use when the user already has candidate creators in mind and wants fit evaluation. It also names alternatives with explicit conditions ('Use semantic_search_creators when you don't have candidates yet', 'Use search_creators first when you only need to resolve rough creator names/handles', 'Use find_lookalike_creators when you want creators similar to known good fits'). Realistic user-phrasing examples reinforce usage.

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