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

The annotations already state that the tool is a read-only, idempotent, open-world operation, but the description adds much more: it says the score comes from a self-developed empirical-weight algorithm, defines every returned field (p, level, gate, match, conds, factors, n) even though there is no output schema, states that ready=false flags missing profile fields, and warns that the probability is a reference value and not a guarantee.

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 purpose and the data source lead the paragraph, and the long list of return fields is labeled and dense, which is justified because there is no output schema. It is a single heavy paragraph, but almost every clause carries information.

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?

The tool has one parameter and no output schema, so the description must cover both the input source and the return shape. It does that completely: it names the field meanings, the readiness gate, and the epistemic caveat about the estimate. Nothing essential for a correct call 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 the single parameter already documents the accepted id formats and the 20-item cap, so the schema carries the burden. The description adds nothing about the ids parameter itself; it only explains the returned fields, so the baseline of 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?

The description names a specific verb and resource: estimate the win probability of bidding on the given notices, using the enterprise profile in the account. It scopes the resource to '这几条公告' (these notices), so it can be told apart from get_notice (fetch a notice) and market_stats (aggregate stats) 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?

It gives clear operating context: notice ids come from search_notices results, at most 20 per call, and the enterprise profile must contain name, region, size, and main sector before results are meaningful. It does not explicitly rule out sibling tools or say when not to use it, which keeps it 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.