Patch skin

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

Annotations only declare readOnlyHint=false, idempotentHint=false and destructiveHint=false; the description adds real behavior beyond them: auto-assigned persistent ids ('<op>-<index>'), graceful skipping with reporting of non-applicable entries, and an in-place file write in 'file' mode. The non-idempotent hint is effectively explained by the retained id assignment. It stops short of covering permissions or error/failure rollback semantics.

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 lead sentence front-loads the core action and its scope, and the remaining sentences each carry distinct information (id persistence, skip-and-report, mode-specific returns). It is dense with parenthetical detail but every clause earns its place, with no filler.

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 mutating tool with full annotation coverage and an output schema, the description supplies the operation set, the id-lifecycle rule, failure handling, and mode-dependent output differences. The main omission is guidance on invalid patches beyond 'skipped and reported' and any permission or workspace prerequisites.

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, but the description adds meaning beyond the schema by contrasting 'spec' versus 'file' outcomes (patched spec + review + sheet vs. write-back + review + sheet) and by explaining that ids assigned to anonymous layers persist for reuse. This is genuine semantic value layered over an already-complete 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?

States a specific verb and resource ('Apply a patch to a spec'), enumerates the operations it supports (update, replace, add or remove layers; change palette, legend or meta), and explicitly relates itself to a sibling ('render the result like texel_render'). An agent can distinguish this from texel_render and the other siblings without opening schemas.

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?

Describes the two operating modes ('spec' vs 'file') and their distinct return behaviors, and implies the patch-then-render workflow relative to texel_render. It does not, however, state explicit when-not conditions or route the agent to alternatives such as texel_validate or texel_diff for non-mutating checks.

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