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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only mentions that results are 'source-backed' and 'machine-readable', which touches on output format but not on rate limits, authentication, side effects (though it's likely read-only), error conditions, or pagination behavior. For a search tool with no annotations, this is a significant gap – an agent doesn't know if the search is expensive, if it mutates anything, or what happens on invalid filters.

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 description is a single, compact sentence that covers the core functionality without extraneous words. It front-loads the search action and lists the key filters, then adds a brief note on output format. This is appropriately concise for the information it conveys, though it could be slightly longer to address other dimensions.

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?

For a tool with 5 parameters, no required fields, no output schema, and no annotations, the description is insufficiently complete. It doesn't explain how multiple filters combine (AND/OR), whether there's pagination or if the 'limit' parameter controls a hard cap, what the output structure looks like beyond 'machine-readable', or any constraints on valid query syntax. An agent would have to experiment or guess to use this tool correctly.

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 only 20% (only 'query' has a description). The description lists keyword, category, tag, and sort order but does not explain the meaning of category enum values (e.g., 'agent-infrastructure' vs 'model-behavior') or sort enum semantics (e.g., what 'usefulness' or 'confidence' mean). It also omits 'limit' entirely. With low schema coverage, the description needed to compensate by clarifying parameter usage, but it stays at a surface level.

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 clearly states the verb 'search', the resource 'niubiagent signals', and the filtering dimensions (keyword, category, tag, sort order). It also adds that results are 'source-backed, machine-readable', which distinguishes this from siblings like get_latest_signals or get_signal that likely return predefined sets or single records. The tool's role as a search endpoint is unambiguous.

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?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention that get_latest_signals is for recent signals or that get_signal is for a specific signal. Usage is only implied by the name 'search', but there is no explicit context about when searching is appropriate or when another sibling is preferred. With zero exclusions or comparisons, the agent must infer routing on its own.

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