Naming Context

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

readOnlyHint=true already tells the agent this is a safe non-mutating operation, and the description adds real behavioral value beyond that: it reuses existing chart 格局/喜用/调候 rather than recomputing, it validates explicit preferences, and it explicitly disclaims a long list of outputs (names, stroke counts, scores, rankings) that an agent might otherwise assume. It does not cover failure modes, such as what happens when record_id does not exist or use_profile is set without a stored profile.

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?

A single front-loaded sentence with a colon introducing the positive capability followed by a semicolon-delimited list of explicit non-capabilities — no filler and no restatement of the title. It is dense but every clause carries information. Slightly heavy punctuation for one sentence, but structure is clear.

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 a 3-parameter tool with a nested 6-field preferences object, 0% schema coverage, and no output schema, the description should also say what the returned context contains. It thoroughly says what is not returned and that the result is 'traceable', but the actual shape and content of the naming context remains vague, and the nested preference semantics are unaddressed.

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 carry the parameter burden, and it partially does: "八字记录或本人资料" explains the record_id vs use_profile oneOf branch, and "校验显式偏好" signals that the preferences object is validated rather than free-form. It adds nothing about the nested preference fields (surname, gender, avoided_chars, preferred_chars, style_keywords, note) or the limits the schema enforces, so meaningful gaps remain at 0% coverage.

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+resource: prepare a traceable naming context from the user's own bazi record or profile, reusing 格局/喜用/调候 and validating explicit preferences. It then draws a hard boundary by enumerating what it will NOT do (no name generation, no 汉字五行, 康熙笔画, 三才五格, 吉凶分, or candidate ranking), which cleanly separates it from any name-generation expectation. An agent knows exactly what artifact this produces without opening the schema.

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?

Gives clear contextual conditions: only for the current user's own record or own profile ("当前用户自己的"), and only as context preparation ahead of naming rather than as a name generator. The negative-scope list acts as an exclusion for the naming task. However, no sibling tool is named (e.g., whether to call bazi.calculate_chart first, or how this differs from bazi.prepare_family_relations_context), so routing is inferred rather than explicit.

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