history_search

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, which cover the safety profile. The description adds meaningful behavioral context beyond annotations: 'Previews may truncate' discloses output truncation, and 'history_read returns full text' points to a workaround. This is valuable non-obvious information that aids agent decision-making.

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 two sentences long, with no fluff. The primary purpose is front-loaded in the first sentence, and the behavioral caveat and alternative are in the second. Every word serves a function, making it highly efficient and easily parseable by an agent.

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?

Given that the tool has 5 parameters with 0% schema coverage and no parameter descriptions from the tool definition, the description is severely incomplete for correct invocation. It does not explain how to structure a query, handle pagination via cursor, or use project/source_id filters. The output schema exists, so return format isn't a concern, but the input semantics are under-documented. An agent would likely need to guess or rely on external knowledge 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 0% – the input schema has no descriptions for any of the five parameters. The description fails to compensate: it does not explain the meaning or usage of query, limit, cursor, project, or source_id. While parameter names like 'query' and 'limit' are somewhat self-explanatory, the description adds zero value in clarifying parameter semantics, and the cursor/project/source_id fields remain ambiguous.

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 a specific verb ('Find') and a specific resource ('literal Unicode text'), which clearly indicates a text search operation. This distinguishes it from the sibling tools history_sources (list sources), history_list (list history), and history_read (read full content). However, it does not explicitly name the target as 'history entries', though the tool name and sibling context imply that.

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 an implicit usage context: use this tool to find literal text, and use history_read to get full text when previews truncate. It explicitly mentions a condition to switch to an alternative, but it does not contrast against history_sources or history_list, nor does it state when not to use this tool. The guidance is partially useful but not comprehensive.

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