search_logs

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

Annotations already declare readOnlyHint=true and openWorldHint=true, and the description usefully adds the required OAuth scope. Beyond that it discloses nothing extra: no mention of the default 2-hour window, pagination via next_slice_key, result caps, or rate limits.

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?

Two short sentences, both carrying information, with the operation stated first. Nothing is padded, though the brevity leaves gaps that could have been filled without bloat.

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 six optional parameters, no output schema, and a pagination token whose reuse semantics matter, the description should say more about paging, default time behavior, and how results relate to sibling tools. The scope hint is the only context offered.

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 83%, so the schema itself already documents sort, query, time bounds, and next_slice_key with examples. The description adds no parameter meaning whatsoever, which is acceptable but no better than baseline.

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 ("Search log records") and even names the backing endpoint, so the agent knows exactly what operation this is. It does not, however, distinguish itself from siblings like aggregate_logs or get_trace_logs, which also read logs and could be confused with a plain search.

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?

"Needs scope logs.read" is an auth prerequisite rather than usage guidance. There is no statement about when to prefer this over aggregate_logs, get_trace_logs, or investigate_problem, and no exclusions or querying-context advice.

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