publish_web_resource

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

Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=false, so the safety bar is lower. The description adds real context beyond that — publishing reflects the 'latest saved version at execution time', which is a meaningful timing guarantee — but it never states what the destructive aspect means in practice (that live consumers see this immediately, and a prior published state is superseded). That is the single most important behavior for a destructive tool and it is left implicit.

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, front-loaded with the verb and resource, then the mechanism, then the usage cases. No filler. Slightly dense packing of the 'without saving/re-uploading' qualifier into the first sentence costs it the top mark.

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?

There is no output schema, so the description should indicate what the agent gets back (success/failure signal, published version info) and it does not. It also omits the dry_run preview path, which is the natural safety valve for a destructive operation. Adequate for purpose and timing, incomplete for a destructive, non-idempotent tool with no return-value documentation.

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 67%: dry_run and the dryRun alias are documented in the schema itself, and only 'id' is undocumented (pattern and required are stated). The description adds nothing about any parameter — it does not even mention the dry_run preview option, which is the one thing an agent should know before invoking a destructive publish. Baseline 3 is appropriate given partial schema coverage.

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 ('Publish a single saved Web Resource'), names the underlying operation ('native PublishXml'), and explicitly carves out what it does NOT do ('without saving/re-uploading content'). That negative clause is what separates it from create_web_resource_and_publish and update_web_resource_and_publish in the sibling list.

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 two concrete use cases: 'save-only workflows' and 'recovery after a publish failure.' It does not name a sibling alternative explicitly, but the 'without saving/re-uploading content' clause implicitly routes the agent away from the combined create/update-and-publish tools. Clear context, no explicit exclusions.

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