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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds genuinely useful behavioral context: what the tool returns (manifest with SHA-256 digests, integrity-check result, reference-only handoff), that include_documents expands the payload, and that document output is capped. It does not contradict the annotations; idempotence is even reinforced by this framing, though not stated outright.

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 sentences, front-loaded with the core action, and the distinguishing scope clause is placed at the end for emphasis. Tight and purposeful, though the document-inclusion detail slightly duplicates the schema.

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 enumerated, yet the description helpfully summarizes the manifest + integrity-check + handoff shape. All 4 params are covered by the schema. The main gap is the absence of routing guidance against siblings, which a complete definition of this pipeline entry point should include.

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 all four parameters, including the 1 MB CSV cap and the ISO 8601 format expectation. The description adds only the include_documents behavior, which is already in the schema's property description, so it adds no meaning beyond structured fields. Baseline 3.

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 a distinctive resource ('Run the toolkit pipeline and return the Decision Pack manifest'), and the closing line 'The pack prepares a decision; it is not the decision' establishes a purpose scope that clearly separates it from validate_passport and check_inventory.

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 description implies usage ('prepare a decision for human review') but never states when to use this tool versus check_inventory or validate_passport, nor any prerequisites such as first validating the inventory CSV.

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?

Annotations already establish readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds genuinely new behavioral context beyond that: output is non-authorizing with authority_effect NONE, results are bucketed by severity, and a sample path exists. It stops short of describing pagination or how findings are structured.

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 compact sentences, with the core action front-loaded before the sample-mode hint and the non-authorization caveat. Nothing is padding, though the parenthetical 'toolkit template columns' is somewhat redundant with the schema and the sentence is dense enough to be slightly hard to scan.

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 no prose explanation, and the description still covers the two input modes, the expected CSV shape, and the non-authorizing nature of the result. What remains missing is only minor: no explicit routing guidance against sibling tools.

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 all three parameters, including the CSV column list, the 1 MB limit, and the ISO 8601 evaluation_time format. The description restates use_sample and the CSV template columns without adding syntax or format detail beyond the schema, so the baseline 3 applies.

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+resource: run policy-as-code checks from the Global AI Governance toolkit against an AI system inventory CSV, returning findings by severity. That is concrete and unambiguous. It does not, however, contrast itself with the siblings build_decision_pack or validate_passport, so an agent gets no explicit differentiation.

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 the described scenario (governance gap checking on an inventory) and the description notes 'Set use_sample=true to run the synthetic sample', which tells the agent one operating mode. There is no explicit when-to-use/when-not guidance relative to validate_passport or build_decision_pack, and no stated prerequisites for the CSV.

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?

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds genuinely useful context beyond that: the demo keys are test-only synthetic keys, and critically that 'Verification is not authorization (authority_effect NONE)', which prevents an agent from misusing the result.

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?

Purpose and scope are front-loaded in the first clause, followed by mode guidance and the authorization caveat. It is a dense single block but every sentence carries information; a list-style breakdown would read more cleanly, hence not a 5.

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 no explanation, and annotations cover the safety profile. The description covers purpose, modes, required parameter combinations, and the important non-authorization caveat. It does not describe failure/error behavior, which leaves a minor gap for a verification tool.

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 100%, so the baseline is 3. The description adds value by explaining the parameter relationships in prose: which parameters pair together (passport_json with trusted_key_json), that revocation_list_json is optional, and that passing example bypasses caller-supplied JSON. That is more than the raw schema conveys.

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 (verify) and resource (Agent Trust Passport) and enumerates precisely what is checked: schema, semantics, Ed25519 signature, key trust, validity window, and signed revocation. This distinguishes it clearly from the unrelated siblings check_inventory and build_decision_pack.

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?

Gives two clear invocation modes and the condition that selects each: use example='signed-unrevoked'/'signed-revoked' for synthetic demos, or pass passport_json (with trusted_key_json, optionally revocation_list_json) for real input. It does not state when NOT to use it or compare against siblings, but the sibling set is unrelated, so a 4 is appropriate.

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