generate_materials

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

With no annotations, the description carries the full burden and does well on the highest-risk behavior: it explicitly says drop_cjk alters the source, is off by default, and describes the ok=false blocking-reason failure mode. Gaps remain on other behavior: mask_secrets (defaulting true) is never explained, nor is whether existing files in output_dir are overwritten.

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?

Four sentences, front-loaded with the outcome and the failure mode, with zero filler. The clause "Pages are drawn from whichever files contain the least Chinese" is dense and slightly cryptic, but it is doing necessary work rather than padding.

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 not be explained, and the tool's core purpose and main risk are covered. For a 9-parameter, 3-required tool with no annotations and no schema descriptions, though, the near-total silence on seven parameters leaves an agent unable to reason about fields, exclude/include or secret masking.

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% across 9 parameters, so the description must compensate and largely does not: fields, exclude, include, mask_secrets, version, software_name and project_root are never explained. Only drop_cjk receives real semantic treatment, and output_dir is only implied by the phrase "into an output directory".

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?

Names a specific verb ("Generate") and enumerates the three concrete artifacts produced (source-code PDF, application form values, verification report) plus the destination (an output directory). It does not distinguish itself from siblings such as estimate_material or check_fields, which likely overlap in the pre-submission workflow, so an agent still has to infer the boundary.

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 implies this is the terminal step that produces submission materials and warns that ok=false means the material must not be submitted, which is useful gating context. However, it never states when to call this instead of estimate_material, check_fields or check_environment, and gives no preconditions (e.g. run check_environment first).

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