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

With no annotations, the description carries the full burden and does well: it states the tool is a pure evaluator whose evaluation instant is an argument ('the cache never reads a clock'), which tells the agent the result is deterministic and independent of wall-clock state. It also discloses the exact header classes consumed and the returned action vocabulary. It stops short of explicitly declaring no side effects or network access.

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 dense sentences, no filler. The purpose is front-loaded, followed by the rule set, the return shape, and the key 'now is an argument' caveat that an agent must not miss. Every sentence earns its place.

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?

For a nested-input evaluator with an output schema (so return values needn't be spelled out), the description covers purpose, rule basis, return vocabulary, and the clock-independence constraint. The remaining gap is the missing editorial distinction between stored.headers and response_headers, and no note on error behavior for malformed dates or missing required fields.

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 75%, so the schema already documents now, stored, stored_at, and age; baseline is 3. The description adds value by naming the semantically relevant headers (Date, Age, Cache-Control, Expires, Last-Modified) and stressing that now must be supplied, but request_headers and response_headers themselves get no explanation and the split between stored.headers and response_headers is never clarified.

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: deciding whether a stored response may be reused without revalidating, computed via RFC 9111 age and freshness arithmetic. That is far more precise than a generic 'evaluate cache'. It never distinguishes itself from siblings such as conditional_evaluate or vary_match, so an agent gets no explicit routing help.

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?

The framing 'Decide whether a stored response may be reused without revalidating' implies the use case (checking cache freshness before serving), but there is no explicit when-to-use, when-not-to-use, or named alternative. An agent must infer that conditional_evaluate handles the conditional-request path instead. Usage is implied, not stated.

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

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

With no annotations, the description carries the full burden and does well: it discloses the precedence order applied, the short-circuit behavior ('stopping at the first applicable one'), and the discrete outcome set (200|304|412) plus the deciding rule and clause references. It stops short of stating that evaluation is side-effect free and does not touch the resource.

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?

A single dense sentence that front-loads the action and then the algorithm and outputs in descending priority. Every clause carries information, though the comma-chained precedence/return list is slightly heavy to parse; a second short sentence would have been cleaner without adding length.

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?

For a nested-schema tool with an output schema (so return values need not be explained) and no annotations, the description supplies the algorithm, precedence rule, and outcome set an agent needs. It lacks only the sibling-disambiguation and side-effect/purity statement, which are modest gaps given how self-contained the tool is.

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 67%, so the schema documents most of method, resource.etag, resource.last_modified, and request_headers. The description indirectly signals which header names in request_headers are meaningful (the four conditional headers), which is some added semantic value, but it explains nothing about how method or resource interact with those headers.

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?

Names a specific verb+resource: judging one request's precondition headers and reporting the resulting status. The scope (If-Match, If-Unmodified-Since, If-None-Match, If-Modified-Since) clearly separates it from siblings like cache_evaluate, cors_evaluate, and vary_match; an agent can route 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?

The RFC 9110 §13.2.2 framing implies the context (HTTP conditional request evaluation), so usage is inferable. However, it never states when to prefer this over cache_evaluate or vary_match, nor any when-not condition or prerequisite (e.g. that resource state must be supplied). No explicit routing guidance.

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

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

No annotations are provided, so the description carries the full disclosure burden, and it does well: 'No network' establishes this as a pure, side-effect-free evaluation, and it enumerates the return shape (decision allow|block, violated rule IDs with clause references, missing headers, remediation headers). It stops short of explicitly stating determinism or that no state is mutated.

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 dense, front-loaded sentences with no filler: purpose first, then output contract, then the no-network constraint. Every clause carries information an agent needs.

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 explained, yet the description still summarizes them usefully. Combined with 7 parameters at 86% schema coverage and the key 'no network' caveat, nothing material an agent needs in order to call this correctly is missing.

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 86%, so the baseline is 3, but the description adds real meaning beyond the schema: 'url is parsed for scheme/host/port only' clarifies how the url parameter is consumed, refining the schema's 'only its origin is used.' It also frames response headers as the object to be judged, which sharpens the nested schema's intent.

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?

Specific verb and resource: 'Judge one HTTP response against the Fetch Standard CORS check,' with the scope constraint that only the URL's origin is used. This implicitly separates it from cors_simulate_fetch (this one does no network work and evaluates a given response), but no sibling is named, so sibling differentiation is inferred rather than explicit.

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 by 'Judge one HTTP response' and by the statement that the URL is only parsed for scheme/host/port, telling the agent this tool takes an already-observed response. However, there is no explicit when-to-use, when-not-to-use, or named alternative (e.g. cors_simulate_fetch) for the case where the agent has no response yet.

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

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 usefully disclose the observed behaviors it reports (origin_set_to_null, credentials_dropped, effective Max-Age), which signals a pure, side-effect-free simulation. It does not state that the tool performs no network I/O, that credentials mode changes mid-chain, or how the simulated stack decides hops, leaving some behavioral questions open.

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 tight sentences, front-loaded with the core action and followed by the reporting surface. Every clause carries information, though the parenthetical event list is slightly list-shaped rather than explanatory.

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 the description legitimately need not spell out return shapes, and it nonetheless sketches them. For a 9-parameter, nested-object tool with no annotations and a sibling that overlaps in intent, the description stops short of the routing and semantics detail an agent needs to call it correctly versus cors_evaluate.

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 78% with 9 parameters, so the schema does most of the documentation work. The description adds no parameter-level meaning at all: nothing explains how is_preflight interacts with redirects, or how mode/credentials shape the hop judgments. Baseline 3 is appropriate given the schema covers most fields, though the description could have clarified the semantically loaded ones.

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 gives a specific verb and resource: it walks a redirect chain hop by hop and judges each hop with the CORS check, and it enumerates the outputs (redirect events, visible headers, effective Access-Control-Max-Age). That is much clearer than a restated name. However, it never distinguishes itself from the sibling cors_evaluate, which an agent could easily mistake for this tool.

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 when-to-use guidance, no statement of prerequisites, and no mention of alternatives, even though cors_evaluate is a direct sibling that plausibly competes for the same intent. The agent must infer from the name alone that this tool is for multi-hop redirect scenarios while cors_evaluate covers a single exchange.

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

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.