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

With no annotations, the description carries the full load. It does disclose one genuinely useful behavioral trait beyond structured data: failures surface via an 'ok' flag rather than an error, triggered by duplicates, invalid URLs, or lint violations. However, it never says whether the tool mutates any stored dossier or is purely a read/compute operation, nor whether duplicate detection is order-sensitive or per-host.

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 short sentences with the two capabilities front-loaded and the failure condition last; no filler. The 'and/or' phrasing is slightly muddy but compactness is good.

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 small two-optional-parameter tool with no output schema and no annotations, the description explains the failure signal but leaves gaps: it never says what a successful response contains (canonicalized URL list? lint finding details?) or what the referenced 'dossier schema' is. That reference is the most important unexplained term in the definition.

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 schema already documents both parameters, and the description only restates that urls are canonicalized/deduplicated and markdown is linted. It adds no format details, such as expected URL scheme or how the markdown is validated against the 'dossier 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?

The description names specific verbs (canonicalize, deduplicate, lint) against specific resources (URLs, a markdown dossier), and the 'and/or' makes clear it is two modes in one tool. The sibling tools (route_agent_seat, evaluate_agent_response) are unrelated operations, so no differentiation is needed.

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 only implied by the parameter split: pass 'urls' to dedupe, 'markdown' to lint, or both. There is no explicit statement of when to call this versus doing the work inline, no mention of prerequisites, and no guidance on what happens if neither parameter is supplied (both are optional).

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 supplied, the description carries the full behavioral burden. It says what is checked but not what happens on a violation (throw, return a verdict object, list of failures), whether checks short-circuit, or whether 'verified source-slice citations' means the tool fetches/validates external sources — a potentially expensive or failing operation left undisclosed.

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 front-loaded sentence with a colon-delimited enumeration — efficient and scannable, with no filler. Density borders on terseness; the facet labels are compressed enough that a reader must infer what 'verified' and 'anchor line' mean operationally.

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?

The tool has two top-level params but a four-field nested contract, no annotations, and no output schema, so the description must cover inputs and outputs alone. Inputs are reasonably covered; the return value — the entire point of an evaluation/check tool — is completely unspecified.

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 50%: only 'response' is documented in the schema, while none of the contract's nested properties (anchor, schema, source, forbiddenClaims) are. The description partially compensates by mapping the four facets to those fields and hinting that the anchor is a line and that source slices are verified, but it gives no format details for anchor, schema, or forbiddenClaims entries.

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 and resource ('Check one agent response against a contract') and enumerates the four contract facets it evaluates: anchor line, JSON payload schema, forbidden claims, and source-slice citations. The scope word 'one' signals single-response evaluation, distinguishing it from batch-oriented siblings like dedup_and_lint_dossier, though no sibling is named explicitly.

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: 'Check one agent response against a contract' suggests a per-response validation call, likely after an agent has produced output. There is no explicit statement of when to prefer this over dedup_and_lint_dossier, no preconditions, and no note on whether the response must already exist or be retrievable.

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 supplied, the description carries the full burden, and it does disclose one genuinely useful trait: it fails closed on unknown roles, modes, or malformed accounting values. However, it never says whether the call is purely a check or whether it persists/consumes budget, nor whether it needs any authorization, nor how the circuit-breaker and judgment-allowance inputs affect the decision. For an unannotated tool with a nested accounting object, that leaves meaningful behavioral gaps.

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, the primary action front-loaded and the error contract second. There is no filler, no restatement of the tool name, and nothing that could be cut without losing information.

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?

The tool takes a nested seven-field accounting object plus two enums and has no output schema, so the description should clarify what an admission decision yields (tier granted, allowance, or refusal) and how the breaker fields interact. It covers the failure contract but not the success contract, leaving the agent unable to predict the response shape. Adequate but with a clear gap given the complexity.

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%, including enum explanations for role and mode and per-field constraints on the budget object, so the schema already does the heavy lifting and baseline 3 applies. The description adds only loose framing ('budget snapshot', 'unknown roles, modes, malformed accounting values') and no interpretation of the judgment/circuit-breaker fields beyond what the schema states.

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 action on specific resources: routing a worker role to a cost tier and admitting planned spend against a budget snapshot. The domain is abstract (seats, tiers, CU), but a reader can tell this is an admissibility/pricing decision rather than a lint or evaluation call, which distinguishes it from the two siblings. It stops short of five because 'route' and 'admit' are internal jargon that a fresh agent may not map to a concrete outcome.

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 explicit when-to-use guidance, no statement of prerequisites (for example that a budget snapshot must be assembled by the caller), and no mention of when not to call it. The only usage-adjacent signal is the failure behavior, which tells the agent what happens on bad input, not when this tool is the right choice.

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