inspect_form_candidate_scope

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

The readOnlyHint=true annotation already establishes the safety profile, and the description is consistent with it while adding two useful facts: both form definitions must be supplied by the caller (nothing is fetched), and the call confers no write or deployment authorization. It still omits what a 'flagged unselected change' looks like in the response and what happens when a supplied hash does not match.

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?

The definition is a single dense sentence plus a short safety fragment, with the comparison semantics front-loaded and no filler. The heavy noun stacking ('explicit reviewed XML paths', 'unselected observed changes') costs a little readability but every clause carries 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?

This is a five-required-parameter, nested-object, hash-pinned comparison with no output schema and almost no schema documentation, yet the description never explains the hashes, the 3000-item cap on approved_paths, or the shape of the result. For a tool of this complexity the description leaves too much to inference.

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 only 17% (only environment_profile is documented), so the description has to compensate. It does map 'candidate and target form definitions' to candidate/target and 'reviewed XML paths' to approved_paths, but candidate_hash and target_hash — both required — are never explained, leaving the integrity-pinning contract invisible.

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 (compare) and specific resources (caller-supplied candidate and target form definitions against reviewed XML paths), and it states the outcome: flagging unselected observed changes. It does not, however, distinguish this from nearby siblings such as compare_environment_forms or review_form_release_scope, so an agent must infer the boundary.

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 or when-not-to-use guidance and no named alternative. The phrase 'No write or deployment authorization' hints that this is a pre-flight inspection rather than an approval, but it does not tell the agent which sibling to pick when it actually wants to review or apply a release scope.

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