link_dependency

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

No annotations provided, so description carries full burden. It explains the effect: making a cross-model dependency with two satisfaction paths. It also describes the unlinking behavior and prerequisite. However, it does not mention idempotency, side effects, or concurrent call behavior.

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?

Concise at about 100 words. Front-loaded with the main purpose. Uses clear structure with bullet-like separation of ideas. No unnecessary words.

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?

With an output schema present (not shown), the description need not cover return values. It covers prerequisites, satisfaction paths, and unlinking. Missing explicit mention of idempotency or potential recomputation triggers, but overall fairly complete.

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 75%, with 'server_version' lacking description. The description adds context for 'target_model_id' (unlinking), but does not explain other parameters beyond the schema. Fails to compensate for the missing schema description of 'server_version'.

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 clearly states the verb ('link') and the resource ('external assumption to a target model'), distinguishing it from siblings like 'add_assumption' and 'submit_attestation'. It also includes the unlinking behavior.

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?

Explicitly describes when to use (linking assumptions to target models), prerequisites (assumption must be linked to control objectives), and alternatives (two independent satisfaction paths, including manual attestation via submit_attestation). Also explains the unlinking case.

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