search_history

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safe read nature is established. The description adds value by noting the output contract — 'attributable evidence, not free-form summaries' — which tells the agent what kind of result to expect and that it should not treat results as synthesized summaries. This is meaningful behavioral context 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?

The description is one short line, front-loaded with the core action and ends with a valuable contrastive note. Every word earns its place. It's appropriately concise for a search tool, though it could be slightly more informative without becoming bloated.

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 an output schema and 7 parameters with rich structural metadata (date-time formats, cursor for pagination, nullable fields). The description covers the search-scope and output-nature aspects but remains thin given the tool's complexity — pagination semantics (cursor), date filtering (since/until), and site/board filtering are entirely unexplained. The output schema helps but the description still under-serves the filtering and pagination dimensions.

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%, so the description must compensate for explaining the 7 parameters. It fails to do so — none of keyword, site, limit, since, until, cursor, or board_key are explained in the description. The only hint is that the tool searches across 'titles, descriptions, and newsflash content' and that keyword is required. With 7 parameters at 0% coverage, this is a notable gap.

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 states the verb+resource ('Search persisted titles, descriptions, and newsflash content') and adds the distinctive 'attributable evidence, not free-form summaries' qualifier, which differentiates search_history from query_history. However, it's relatively terse and doesn't fully clarify how this differs from the closely named sibling 'query_history' — the differentiation is implied rather than explicit.

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 its siblings. Given siblings like 'query_history' and 'fetch_current', there is no statement about what scenarios call for search_history specifically, nor exclusions. The agent receives no help choosing among the closely related search/query tools.

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