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

It discloses partial-update behavior, scope re-assignment semantics, and the fact that enabled=false hides rather than deletes. These go beyond the bare annotations (readOnly=false, destructive=false) and help the agent understand the operation's effects. It does not mention null-vs-omit semantics, but it does not contradict any annotation.

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, each carrying distinct value: the partial-update rule, scoping behavior, and the hide-not-delete behavior. It is front-loaded and contains 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?

The description covers the trickiest aspects (scope and enabled behavior) and an output schema exists, so return values need no explanation. The main gap is the null-vs-omit semantics for clearing fields like body or description, which is especially relevant because most parameters are nullable and default to null. This could lead an agent to accidentally null a field by passing null when it meant to leave it unchanged.

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 0%, so the description must compensate. It does explain project_id and enabled meaningfully, and the 'pass only fields you want to change' rule clarifies the general PATCH-style usage. However, name, body, and description are left to inference, and the schema's nullable values make the distinction between omitting a field and passing null ambiguous.

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 opens with 'Update a skill' — a specific verb and resource — and immediately clarifies that it is a partial update ('pass only the fields you want to change'). It also distinguishes itself from delete_skill by noting that disabling a skill hides it 'without deleting it.'

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 gives clear conditional usage: pass project_id to attach, pass 'global' to make global, omit project_id to leave scope unchanged, and set enabled=false instead of deleting. It does not explicitly say 'use create_skill for new skills,' but the context of updating an existing skill makes that reasonably clear.

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