fetch

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so safety is covered. The description adds genuinely non-obvious behavior: window=0 returns the full parent section rather than the small indexed block, and truncated=true signals a character-limit cut. It doesn't discuss ordering or size limits, but the important behavioral quirk is disclosed.

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-loaded with the action, then two labeled sections for when/when-not, then the window=0 caveat. Efficient overall, though the bold emphasis markers and the 'main tool for evidence' positioning sentence are slightly redundant given the surrounding text.

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?

Three optional parameters, an output schema already present, and annotations covering safety — the description supplies exactly the missing pieces (mode selection, window=0 behavior, truncation flag) and need not restate return values.

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 the baseline is 3; however the description explains the special semantics of window=0 (parent-block return) that the schema's 'expand N chunks' wording does not convey, and frames doc_id/chunk_id as alternative whole-document vs. chunk reads. This is meaningful meaning added on top of the schema.

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?

Description states a specific action pair — fetch surrounding context for a matched chunk, or read a whole document by doc_id — and labels itself the primary evidence-retrieval tool. It is clearly distinguishable from 'search' (existence checks) and 'list_sources' (enumeration).

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?

Contains explicit 何时用 (when the snippet is insufficient / full clause needed) and 何时不用 (just confirming a document exists — search suffices) sections, naming the sibling tool that covers the excluded case. Routing is fully determined.

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