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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely non-structured behavior: it normalizes real-world spelling drift (spacing, suffixes, punctuation) and returns a confidence score with a 0.6 trust cutoff. It omits what happens when nothing matches at all.

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?

Three short sentences: what it does, why it exists, and the decision threshold. The confidence cutoff is stated last where it is most actionable, and there is no filler.

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?

With no output schema, the description carries the burden of describing returns, and it does name the two outputs (slug, confidence score) plus the interpretation threshold. It leaves one gap: the no-match / low-confidence fallback behavior is undefined, which an agent would need before deciding what to do next.

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 coverage is 100% for the single parameter, so the baseline is 3. The description earns an extra point by illustrating the input's expected messiness with concrete variants ("Soneva Fushi" vs "SonevaFushi"), which tells the agent it need not pre-clean the string.

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 states a specific verb and transformation (loose name -> canonical slug plus confidence score), which is clearly distinct from fetching (get_resort) or searching (search_resorts). It stops short of naming those siblings to make the boundary explicit, so it lands at a strong 4 rather than a 5.

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?

Usage is implied rather than stated: the agent can infer this is for user-authored names that need normalization, and the 0.6 threshold gives actionable guidance on evaluating results. But there is no explicit "use this instead of get_resort/search_resorts" routing instruction, which matters given the crowded sibling set.

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