search

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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), so the bar is lower. The description adds two genuinely non-obvious behaviors: results are file:line locations rather than symbol references, and hits are paginated inside task artifacts rather than returned inline. It still omits how artifact pagination is consumed, but it goes meaningfully beyond the annotations.

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 short clauses, front-loaded with what is searched, then what is returned, then what it is not, then how results are delivered. No filler or redundant restatement of the name.

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 appropriately states the return shape, and it explains result delivery via artifacts. For a five-parameter search tool with zero schema documentation, however, it leaves regex semantics and directory scoping unaddressed, which an agent needs in order to invoke it 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 0% across five parameters, so the description must carry the burden. It only hints that limit/offset pagination exists ('结果在任务产物中分页') and says nothing about 'directory' (search root) or 'regex' (whether the query is a literal or pattern), leaving the most easily misused parameters unexplained.

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: searching already-exported/decompiled source code, returning file:line hits. It explicitly contrasts with 'DEX xref', which is the key disambiguation from the sibling 'dex' tool. The only weakness is that 'exported source' is not pinned to a specific export type, but an agent can still tell what this tool does.

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?

'不是 DEX xref' gives a negative routing hint, effectively saying not to use this when cross-reference analysis is needed. However, no positive when-to-use guidance is given and no alternative tool is named for the xref case, so the exclusion is implied rather than explicit.

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