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

Annotations already carry the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false), so the bar is lower. The description adds one useful behavioral nuance: the resource is public ('published') and optionally personalized with a secret. But it does not disclose what happens with an invalid secret, whether the public view works with zero params, or any other edge behavior — modest value beyond annotations, no contradiction.

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?

Thirteen words, endpoint front-loaded, zero filler — efficiently structured as three punchy fragments. It earns its brevity by leaving heavy lifting to the schema and annotations. The only cost is that the metaphor carries semantic weight that clarity scoring already penalizes.

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 a rich annotation set, a 100%-documented schema, an output schema present, and zero required params, most operational context is covered elsewhere. The real gap is conceptual: the description never explains what a 'cap' or the 'ladder' is, which is the information an agent most needs to select this tool over its many siblings. Sufficient mechanics, insufficient semantics.

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 — and the schema descriptions are unusually rich (nonce provenance, leave_token auth mapping and never-logged guarantee, signature/key formats). The description's 'with a secret, your own rung' adds only a hint that a secret parameter enables personalization, without identifying which parameter, so it does not meaningfully exceed the baseline.

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 names a specific verb and resource ('GET /api/caps') and conveys the core concept: a published ranking ('ladder') that becomes personalized ('your own rung') with a secret. This sets it apart from generic list siblings like card_list or plaza_list. However, the 'ladder/rung' metaphor is unexplained, leaving ambiguity about what 'caps' actually represents — not quite the precision of 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?

No explicit when-to-use, when-not-to-use, or alternative tool guidance is present. None of the 44 siblings are referenced, so an agent must infer from the metaphor alone when caps is the right call versus checkpoint, lot_status, or own. The read-only GET implies a lookup use case, but that is left entirely to inference.

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