photoshop_guard_resume

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

With no annotations, the description carries real behavioral weight: it says uncertain mutations are not replayed, that a pixel/owner comparison happens internally on same_document_confirmed=true, and that mismatch leaves work quarantined. That is meaningful disclosure of a safety-critical behavior; it falls short of 5 only because permissions, side effects, and failure surfacing are unstated.

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 with no filler, and the core behavior (recover without replaying mutations) is front-loaded. The density of internal jargon ("preserved frame", "fresh pixels/owners") makes it slightly harder to parse than it needs to be.

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 5-parameter, zero-required, no-output-schema, no-annotation tool, the description covers the recovery path and the confirmation flag but is silent on the ownership projection mode and director_fields usage beyond a terse "use a separate call for identity recovery." Adequate but with clear gaps for an agent choosing among parameter combinations.

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 already 80%, so the baseline is 3; the description earns above baseline by explaining what same_document_confirmed actually does (requires user confirmation and triggers an internal pixel/owner comparison) rather than merely restating the flag. It still says nothing about projection=ownership, owner_id, or director_fields semantics that the schema does not already carry.

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?

Uses a specific verb (recover) on a specific resource (the local Photoshop workflow) and states the defining constraint: uncertain mutations are not replayed. It is distinguishable from siblings like photoshop_guard_reconcile or photoshop_guard_recover_lock, though it never names an alternative 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?

"Keep it unless the user explicitly changes execution mode" gives persistence guidance rather than selection guidance, and the UXP-session-change sentence implies the triggering context. There is no explicit statement of when to prefer this over siblings (e.g. reconcile vs recover_lock), so the routing must be inferred.

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