vary_match

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

No annotations are supplied, so the description carries the full burden. It does disclose meaningful behavior: comparison is governed by each field's normalisation policy and the result is a hit/miss classification plus differing fields and rule IDs, which implies a read-only, deterministic evaluation. It does not state the safety profile (pure function, no mutation, no network or auth) or how missing headers are treated.

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?

Two sentences, front-loaded with the decision and the normative basis, with the return payload listed afterwards. Dense but every clause carries information; no filler or tautology.

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?

An output schema exists, so return values need not be elaborated (the description nonetheless enumerates them). For a nested two-object computation grounded in an RFC, the definition covers intent and output but omits the parameter-to-field mapping and edge-case semantics, leaving an agent with gaps given 0% schema description coverage.

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 has to compensate for two required nested-object parameters. It does convey the split semantically — the stored Vary value with headers at store time versus the incoming request headers — but never maps this onto the cached.vary, cached.request_headers_at_store and incoming.request_headers fields by name, and says nothing about repeated-header or array handling.

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 a specific verb ('Decide whether') and a precise resource (a stored response can be reused for an incoming request), anchored to RFC 9111 section 4.1 and the Vary mechanism. It is far more specific than the sibling names alone, though it never explicitly distinguishes itself from the conceptually adjacent cache_evaluate.

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?

Use is implied by the RFC citation and the 'stored response vs incoming request' framing, but there is no explicit when-to-use, when-not-to-use, or pointer to alternatives such as cache_evaluate or conditional_evaluate. The agent must infer routing from the RFC reference.

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