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

Adds substantial behavior beyond annotations: required Microsoft sign-in with blog.write scope, single-use link, 15-minute expiry, presentational constraint never to fetch the link, access limited to the engineer's own drafts/posts with site-owner exception, and a note that the email editor link is unaffected. Annotations already mark it non-read-only and non-idempotent, and the description consistently reinforces that.

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 auth requirement and trigger are front-loaded, and most sentences carry distinct operational value. It is slightly dense and parenthetical in the parameter-routing sentence, and the final email-link sentence is useful but tangential.

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 an output schema, the description need not explain return values. It still covers auth, link lifetime, single-use behavior, presentation rules, access scope, and parameter routing, leaving no major operational gap for an agent invoking this tool.

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 100%, so the schema already documents `id` and `post`. The description adds only limited nuance: it clarifies that a published draft's id can be used with `post` and that the revision behavior matches revise_post, but it does not add new syntax, format, or exclusivity constraints beyond what the schema implies.

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 action and output: a browser-editor link that works once and expires in 15 minutes, for a draft or published post. It distinguishes the tool from revise_post by noting that `post` opens or finds the post's revision 'as revise_post does', making the boundary clear.

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?

Explicitly says when to use it: when the engineer asks to open or edit a draft or published post in the browser. It also gives a strong presentation rule ('Show it to them as a link and say so; never open or fetch it yourself'), but does not explicitly state when to use revise_post instead, only that the revision behavior is shared.

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