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

Beyond the annotations (readOnly=false, idempotent=true, destructive=false), the description discloses that every save inserts a revision, that the default mode is last-write-wins, and that a no-op save returns no_changes=true without inserting a revision. That is genuine behavioral context. It does not mention permission requirements or the tenant-ambiguity refusal path.

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 tight sentences, each carrying distinct information (what it does, omit semantics, concurrency mode, no-op result), with the core action front-loaded. 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?

An output schema exists, and the description still flags the one non-obvious return value (no_changes=true) that governs caller behavior. For a mutation tool with full schema coverage, this covers what an agent needs; only permission/tenant edge cases are left entirely to the schema.

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 each parameter is already documented individually. The description restates the preserve-on-omit rule that the schema already states per field, and only marginally enriches expected_revision_id with the last-write-wins default. Baseline 3 is appropriate.

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?

"Save a new revision of an existing document" gives a specific verb (save/revision) and resource, and implicitly separates it from kb_documents_create. It does not explicitly contrast with the edit_begin/apply/commit family or revisions_restore, which are the nearest alternatives.

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?

Clear conditional guidance for the important choices: omit fields to preserve values, pass expected_revision_id for concurrency protection, omit for last-write-wins. No sibling tool is named as an alternative and no when-not-to-use case is given, so it stops short of a 5.

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