generate_student_doc

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

With no annotations, the description does carry real behavioral weight: it discloses that a local rendering script is executed and that output defaults to outputs or /tmp when output_path is omitted. It does not disclose overwrite behavior when output_path already exists, failure modes for an invalid skill_name, or filesystem/permission implications of writing a file.

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?

One purpose sentence followed by a tight parameter list, with the conditional note about demo mode attached directly to the data parameter. No filler or repetition.

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?

An output schema exists so return values need no explanation, and the description covers all five inputs plus default-path behavior. The remaining gap is the undocumented shape of the `data` dictionary and which sibling tool produces it, which matters for correct pipeline sequencing.

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 0%, so the description must compensate, and it largely does: every one of the 5 parameters is explained, school enumerates accepted template values (tsinghua, pku, whu, zju, default) that are absent from the schema, and skill_name gives example values. The only shortfall is that the valid skill_name set is open-ended ('等') and must be discovered via list_student_skills.

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 artifact: it renders structured application data through a local script into a standard .docx. That is concrete and distinguishable from siblings like list_school_templates or simulate_student_review, but the description never explicitly contrasts itself with them or says which upstream tool supplies the data.

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?

Usage is only implied: you generate after having collected structured data, and demo=True is offered as a fast trial path. There is no explicit statement of when to prefer this over route_student_skill or get_skill_requirements, nor any prerequisites such as 'run get_skill_requirements first'.

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