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

Even though annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, the description goes far beyond that. It discloses that each record includes nine dimensions, weighted totals, evidence-backed penalties, cited source URLs, and metadata, and it even provides the exact scoring formula per rubric version. This is rich behavioral context that lets an agent understand what the tool returns and how scores are constructed, with no contradiction of the annotations.

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 extremely long and densely packed, with extensive detail about six research dimensions, weighting formulas, and rubric versions (v2/v3/v4). While this detail is informative, it is not concise for a tool description; the key behavior (returns list or single person) is embedded in a wall of text. It is front-loaded with the index definition but quickly becomes over-specified.

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?

There is no output schema, so the description carries the burden of explaining return values, and it does so comprehensively: it describes the ranked list, per-person records, nine dimensions, penalties, source URLs, and the verification formula. It is nearly complete, but some variables in the formula (e.g., H and I) are not explicitly defined, and the claim that 'popularity, fundraising and media coverage carry zero' versus the formula's use of H+I+SF creates slight ambiguity for an agent trying to re-verify scores.

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% coverage, with descriptions for both 'slug' and 'limit'. The description adds a little extra meaning for 'slug' by indicating that omitting it returns the whole list and including it returns one person, but it provides no additional semantics for 'limit'. This matches the baseline of 3 for high schema coverage.

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 that this tool returns a ranked list of founders and CEOs based on an AI expertise index (0-100), or a single person when a slug is provided. It names a specific resource (the CEO AI Expertise Index) and its distinguishing action ('Returns the full ranked list, or one person with ?slug='), which differentiates it from the many other get_* sibling tools.

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?

There is no explicit guidance on when to choose this tool over alternatives. It does explain the two invocation modes (omit slug for the full list, include slug for one person), but this is parameter usage rather than use-case guidance. No sibling tool is mentioned or contrasted, so an agent is left to infer when this index is the right resource.

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