intelligence_extract_entities

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

Annotations already declare readOnly, idempotent, openWorld, and non-destructive. The description adds value by noting the use of the client's LLM and by including 'sampling_used' in the return shape, which hints that sampling may occur for large inputs. This provides behavioral context beyond the annotations without contradiction.

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?

The description is compact, well-structured with bold labels (Purpose, When to use, Returns), and front-loaded with the core purpose. Every sentence provides useful information without waste, making it easy for an agent to scan.

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?

The description covers purpose, use cases, and return shape, and is supported by strong annotations and a complete schema with an output schema. It sufficiently explains the tool's role within the intelligence suite, so the agent can select and invoke it correctly. Minor omissions like explicit limitations are not necessary given the schema and annotations.

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 schema fully documents all three parameters. The description lists entity types in the purpose, which overlaps with the schema's entity_types enum, but it does not add additional param-level semantics beyond the schema. Baseline 3 is appropriate.

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 description uses the specific verb 'Pull structured entities' and names the resource ('recent Discord messages') with concrete entity types (decisions, action items, dates, mentions, URLs, code). This clearly distinguishes it from sibling intelligence tools like summarize or classify, which serve different outcomes.

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 'When to use' section lists three concrete use cases (post-meeting recap, audit log of decisions, weekly digest builder), giving clear context for when the tool is appropriate. It does not explicitly mention alternatives or when not to use it, so it misses the top tier.

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