extract_entities

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds beyond that: it discloses the 'enhanced intelligence mode' requirement, states the tool is stateless, and explicitly lists the returned fields (people, organizations, technologies, projects, relationships, keywords). This is valuable context an agent needs but would not know from annotations alone.

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 moderately detailed but every sentence carries meaning: purpose, entity types, relationship types, requirements, safety (repeats annotation), and return shape. It is front-loaded with the purpose and specifics. The only minor redundancy is 'Read-only, stateless' which partly duplicates annotations, but it is brief and not harmful. Overall, it is appropriately concise for a tool with no output schema.

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 single-parameter NLP tool with no output schema, the description is very complete: it defines input type and expectations, lists all output categories, states the mode requirement, and clarifies it is stateless. Siblings are unrelated, so no additional disambiguation is needed. An agent is fully equipped to call this tool correctly without external guidance.

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 schema documents the 'text' parameter at 100% coverage, so the baseline is 3. The description adds extra semantics not in the schema: 'Longer text yields more entities' and 'Supports natural language, code comments, or structured text.' These hints help an agent decide how much text to provide and what formats are acceptable, thereby exceeding the schema's basic type and description.

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 explicitly states the verb 'Extract' and the resource 'named entities and relationships from text using NLP', and enumerates the entity types (people, organizations, technologies, projects) and relationship types (WORKS_FOR, USES). It is clearly distinct from sibling memory-management tools, which focus on storage/retrieval rather than extraction, so an agent would have no trouble selecting it.

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 description does not name a specific alternative or exclusion, but the sibling tools are all memory-related and have no overlap, so the intended usage context is obvious. It does include a critical usage condition: 'Requires enhanced intelligence mode', which tells the agent when it can be invoked. It also notes the tool is read-only and stateless, implying it is for analysis, not modification.

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