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

Annotations already declare readOnly/idempotent/openWorld safety, and the description layers on real operational facts: login required, friend content requires mutual follow, blocked/deactivated accounts return empty, and pagination must pass nextCursor verbatim until null. This goes well beyond the annotation surface.

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?

Front-loads the login requirement and packs pagination, return shape, and sibling routing into a few semicolon-delimited clauses with no filler. Slightly telegraphic abbreviations make it denser than ideal, but every clause earns its place.

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 read-only list tool with no output schema, the description supplies the missing return context: card content is truncated to 2 comments, total/muted appear on the homepage listing, cursor termination is null, and empty results are explained for blocked/deactivated users. An agent has what it needs to call and interpret it.

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%, so baseline is 3, but the description adds genuine semantics: cursor is the prior page's nextCursor passed unchanged until null, and truncation should be handled by lowering limit. It meaningfully extends the schema text rather than repeating it.

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 (fetch someone's moments) and scope (defaults to self), and explicitly routes to siblings: get_moment for full text, get_creator to view a person, start_conversation to contact. Docked one point because fragments like '首页total/muted' are cryptic and rely on unstated context.

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?

Explicit when-to-use and when-to-use-something-else: cards show only the 2 latest comments so use get_moment for full text; if truncated, reduce limit; get_creator for the person, start_conversation to reach out. Alternatives and conditions are named, not inferred.

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