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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, and the description adds substantial behavioral detail beyond that: pagination caps at 100, the need to check 'next_start_record', the preview-only nature of returned text, and the under-matching of English queries. These are critical runtime behaviors not covered by annotations. No contradiction exists.

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 longer than average but every section earns its place: purpose, language guidance, pagination warning, and pointer to get_speech. It is front-loaded with the main action and scope. Minor redundancy exists with the schema's parameter descriptions, but overall it is well-structured and not padded.

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 an 8-parameter, 0-required search tool with no output schema, the description covers the essential return fields (speaker, party, house, etc.), pagination mechanics, and language constraints. It does not enumerate every edge case (e.g., exact date formats) but provides enough for an agent to call it correctly. The absence of an output schema is partially mitigated by the description's listing of returned attributes.

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 coverage is 100% and the schema itself contains rich descriptions for every parameter (e.g., query explains AND semantics and English under-match, start_record explains pagination). The tool description adds little beyond the schema for parameters; it repeats some points (Japanese-first) but does not provide new semantic meaning. A baseline of 3 is appropriate.

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 ('full-text search'), a resource ('Japanese National Diet speeches'), and a scope ('back to 1947'), and explicitly contrasts with get_speech by noting the preview vs. full-text distinction. It clearly distinguishes the tool from its siblings, such as search_meetings and search_within, by focusing on speeches and the NDL API.

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 clear context on when to use the tool (searching speeches) and explicitly routes the agent to get_speech for full text. It also advises on language use (Japanese-first) and pagination handling. However, it does not explicitly exclude use cases or mention alternatives like search_meetings or search_within, so it stops short of a full when-not list.

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