deepseek_extract

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

Annotations already declare readOnly, idempotent, openWorld, and non-destructive, so the safety profile is covered. The description adds value beyond that: it states the result is returned under 'data', that full page text is not returned, that caching exists and can be bypassed via refresh, and that escapes/boilerplate are cleaned by default. Missing only rate limits, auth/cost behavior, and extraction failure semantics.

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?

Purpose and sibling routing are front-loaded in the first paragraph, followed by a compact Args list where each line carries distinct information. The only waste is echoing defaults already visible in the schema and one near-tautological parameter gloss.

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-value detail is not required, yet the description still tells the agent where the payload lives ('data'). Combined with the field/schema exclusivity rule and the cache/fetch controls, an agent has everything needed to invoke it correctly.

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 carries the full burden and does document all eight parameters with intent, not just names — notably the mutual exclusivity of fields and schema, which the schema does not express at all. Defaults are restated (clean, max_chars, refresh, strip_boilerplate), which is mildly redundant, and a couple of glosses are thin ('schema: JSON Schema defining target structure', 'instruction: Optional extraction guidance').

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?

The opening sentence names a specific verb (extract), a specific resource (web page), and a specific output shape (structured JSON conforming to fields or a schema). It further scopes the tool negatively ('without returning full page text'), so an agent can distinguish it from deepseek_fetch and deepseek_search 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?

Explicit exclusions are given with named alternatives: 'Do not use for general reading (use deepseek_fetch), nor for search or discovery (use deepseek_search).' This is exactly the when-not/alternative routing an agent needs, and it names two of the six siblings directly.

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