attach_signal

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

Annotations already declare this is a non-read-only (write), non-destructive operation with external world interaction. The description adds domain context by clarifying that signals represent 'external feedback', adding semantic meaning beyond the structured annotations. It does not address idempotency, conflicts, or side effects, but meets the lowered bar for annotated tools.

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 consists of two efficient sentences: the first states the action, the second provides domain context. No redundancy or filler content exists. Every sentence earns its place by conveying distinct information (mechanism vs. domain meaning).

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?

Given the tool's simplicity (2 flat required parameters, 100% schema coverage, no output schema), the description is appropriately complete. It explains the relationship being created (feedback-to-idea association). Annotations handle the safety profile (non-destructive write), so the description need not repeat this. Could mention error conditions (e.g., if IDs don't exist) for a 5.

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?

Input schema has 100% description coverage with clear parameter definitions ('The ID of the signal to attach', 'The ID of the idea to attach the signal to'). The description reinforces the parameter concepts by mentioning 'signal' and 'idea' but does not add syntactic details or format constraints beyond what the schema provides. Baseline score 3 applies per rubric for high schema coverage.

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 specific verbs ('Link', 'associates') and resources ('signal', 'idea'). It clarifies domain semantics by defining signals as 'external feedback' and ideas as 'product ideas'. However, it does not explicitly distinguish from sibling tool 'create_relationship', which also creates associations between entities.

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 implies usage through domain context ('external feedback with a specific product idea'), suggesting when you have customer feedback to attach to an idea. However, it lacks explicit when-to-use guidance, prerequisites (e.g., requiring both signal and idea to exist first), or comparison to alternatives like create_relationship.

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