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

Adds substantial context beyond the annotations: it discloses the auth requirement (Microsoft sign-in, scope blog.write) and that anonymous calls receive a sign-in challenge, the state precondition, the base_sha freshness requirement, and post-execution behavior ('commits it and rebuilds the preview'). None of this is in the structured fields, and nothing contradicts the annotation profile.

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?

Dense and mostly front-loaded, but the lead sentence is the auth precondition rather than the tool's action, and phrasing like 'only while it waits on you (state drafted)' takes work to parse. Every sentence still carries information; the cost is readability, not redundancy.

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?

With no output schema, the description compensates by describing consequences (commit, preview rebuild) and explicitly ruling out publication. It does not state what is returned (e.g., a new sha) or what happens on a stale base_sha, which a save tool arguably should.

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 real meaning by tying base_sha to get_status and framing it as the version the edit started from, which conveys the optimistic-concurrency semantics the schema description only hints at. The id/markdown semantics are left largely to the 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+resource ('Save a new version of one of your own drafts') and anchors it to a familiar analogue ('as the browser editor's Save does'). It also explicitly separates itself from submit_draft ('Never publishes') and check_draft ('it runs no checks'), so an agent can distinguish it from siblings without opening a schema.

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?

Gives explicit when-conditions: only in state 'drafted', only on top of the version you edited, and never while the draft is open in the browser editor. It also names the alternative tool for validation ('check_draft does') and explains that Run checks, not this tool, is what Publish needs.

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