Model digest

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

With no annotations, the description carries the full burden and mostly succeeds: it discloses ambiguity handling ('Ambiguous names return a candidate table'), error behavior for invalid sections ('Unknown names error with the valid list'), caching semantics ('refresh: bypass the cache and re-fetch'), and the round-trippable slug in header/footnote. It does not mention auth or whether the call has side effects, which is a minor residual gap.

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?

Front-loaded summary sentence, then a short usage sentence, then a compact Args block that keeps each parameter to one to two lines. No filler; every clause carries information an agent needs to invoke the tool.

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?

Despite no output schema and no annotations, the description covers the return categories, the ambiguity path, error cases for bad section names, the slug round-trip, and all inputs. An agent has everything required to call it correctly and to interpret an ambiguous result.

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 0%, so the description must compensate fully — and it does: it documents query's fuzzy matching and ambiguity fallback, enumerates the valid section names, gives the default set, notes the 'specs = identity' alias, and explains that refresh bypasses the cache. All three parameters are meaningfully specified beyond the bare types in the schema.

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?

States precisely what is returned for a single resource — 'One model's full digest: specs, indices, benchmark scores, pricing and speed' — and immediately differentiates from the leaderboard/search siblings. An agent can tell that this is the deep single-model view rather than a list view without opening the schema.

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?

Explicitly positions the tool in a workflow: 'Use after aa_leaderboard/aa_search when you need everything about a single model,' naming the alternatives. It stops short of stating when NOT to use it (e.g., for multiple models use aa_compare), so the exclusion side is inferred rather than stated.

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