Разделы модели

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds the useful behavioral fact that the response carries per-section object counts and descriptions, though it does not mention size, paging or whether the section list is exhaustive.

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?

Three short sentences, front-loaded with the 'when to call' trigger, then the return content, then the next-step routing. Every clause carries information; no filler.

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 parameterless discovery tool with no output schema, the description supplies everything needed: when to call it, what comes back (section identifiers plus counts and descriptions), and which sibling to chain into. Nothing an agent needs in order to invoke it correctly is missing.

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?

The tool takes zero parameters and the description correctly implies no input is needed, so there is nothing to mis-specify. No meaningful parameter semantics remain to be added.

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 resource: it returns the seaf.company.* sections together with an object count and a description. It also explicitly separates itself from inspect_sections and describe_section, so an agent can pick it out of a crowded sibling list without opening any 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 an explicit trigger ('at the start of work, or when it's unknown which section holds the data') plus named alternatives with the distinguishing condition for each: inspect_sections for structure and samples of several sections, describe_section for one section without samples. Both when-to-use and the routing decision are handed over directly.

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