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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false; the description adds real context by scoping the effect to the unpublished draft and stating the published version is untouched until publishIcp, which meaningfully bounds the blast radius. It also discloses the optimistic-concurrency check against the draft revision, which annotations do not cover. Minor deduction because 'Repeating the call with the same input leaves the same result' essentially restates idempotentHint=true.

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 short sentences, front-loaded with the core action, then the scope of effect, then the idempotency note. No filler and nothing buried.

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?

Given a very large nested body schema, no output schema and tool-level annotations that cover the safety profile, the description covers effect scope, revision checking and idempotency well. It still leaves open what happens on a revision mismatch (error vs. overwrite), what the response contains, and how partial updates behave against the existing draft.

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 carry the load; it does explain the intent of name, definition and expected_revision ('checked against the draft revision' conveys optimistic concurrency, which the bare integer field does not). However, with a deeply nested definition object, it says nothing about whether name and definition are partial or full replacements, nor about the valid schema_version variants.

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 ('Saves a new name or definition to an ICP's unpublished draft') and pins the target to the draft rather than the published ICP. It clearly separates itself from publishIcp, though it does not explicitly contrast with the closely related createIcpDraft or the update tools in the neighborhood.

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 sentence 'The published version is unchanged until publishIcp' implies the intended window of use (editing before publishing) and names the tool that follows. There is no explicit when-to-use / when-not-to-use statement, and no mention of what to do if the revision check fails or which sibling to pick instead.

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