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

Goes well beyond the annotations by disclosing that the call consumes a scarce, vendor-computed daily quota, that it is a mutation despite destructiveHint=false, and that failure modes return as normal results rather than thrown errors — exactly the runtime behavior an agent needs to plan around.

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?

Front-loads the operation, then cost model, then result semantics in three dense sentences with no filler; the long final sentence earns its length by enumerating the exact non-error return states.

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 spelling out the result envelope (ok:false plus reason values) that the agent will actually receive, and covers cost, scope, and preconditions — nothing material is missing.

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% and both parameters are self-documented, so the schema carries the load; the description only adds the implicit constraint that the URLs must belong to the project itself. 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?

States a precise verb + resource ('Push a project's own URLs to Baidu') plus the exact upstream endpoint, so an agent can distinguish it immediately from siblings like submit_bing_feed, submit_indexnow, and reindex_yandex_url.

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?

Makes clear context: it is FREE (no credits) but spends the real Baidu daily quota, and it describes the operational preconditions behind its result codes. It does not explicitly name the alternative tools (submit_indexnow / submit_bing_feed) or say 'use this only when you have a Baidu connection', leaving that to inference.

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