photoshop_guard_reconcile

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

With no annotations, the description carries the burden and does disclose meaningful behavior: it will not replay the operation and Guard collects fresh document-list evidence internally rather than trusting caller-supplied evidence. However, it never states what happens on success/failure, whether the barrier/state is cleared, or what permissions or preconditions apply, leaving significant 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 compact sentences, front-loaded with the action and immediately followed by the exact invocation recipe and a prohibition. Dense but no filler; the only cost is the heavy internal shorthand.

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?

No annotations and no output schema, and only 38% of 8 parameters are schema-documented, so the description needed to do more. It covers the primary recovery path adequately but omits what the tool returns, how the alternate evidence-supply path (documents_id/capture_evidence) relates to the closed-document path, and what state_id/preview_id are for.

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 only 38% across 8 params, so the description must compensate. It explains id, outcome=abandoned, document_closed_confirmed, reason, and implicitly documents_id ('do not manufacture evidence ids'), but leaves state_id, preview_id, and capture_evidence entirely unaddressed even though those are the parameters most likely to confuse a caller.

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+resource ('Reconcile uncertain execution') plus a key constraint ('without replay'), which distinguishes it from replay-style siblings like photoshop_guard_resume. The wording is domain-jargon heavy ('uncertain execution', 'Guard'), but the core action is identifiable.

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 an explicit trigger condition ('For a user-confirmed closed document') and the exact call shape to use in that case (id + outcome=abandoned + document_closed_confirmed=true + reason). It also states a prohibition ('Do not read source or manufacture evidence ids'), though it does not contrast against sibling recovery tools such as guard_recover_lock or guard_resume.

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