cos_learn_suggest

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

Beyond the readOnly and idempotent annotations, the description explains the spaced repetition mechanism (fading patterns with 0.2-0.4 confidence) and the return format, giving valuable insight into how results are prioritized. This goes well beyond the annotations.

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 well-structured and concise: a clear one-sentence purpose, a single behavioral note, then a structured Args list and Returns. Every sentence adds value with no redundancy.

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 read-only tool with four optional parameters and an output schema, the description covers the purpose, behavioral details, parameter semantics, and return format. The only missing detail is a fuller definition of 'current task context', but that is likely implicit. It is complete enough for reliable invocation.

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 has zero property descriptions, so the Args section is essential. It provides meaningful explanations for each parameter, including examples for domain and task_type and a range for limit. The complexity parameter could be more explicit about allowed values, but overall it compensates well for the schema gap.

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 tool returns relevant patterns for the current task context, specifying the action and resource. It distinguishes itself from siblings like cos_learn_extract and cos_learn_validate by focusing on suggestion rather than extraction or validation.

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 provides clear context by mentioning 'current task context' and the spaced repetition prioritization, indicating when to use it. However, it does not explicitly contrast with alternatives or state when not to use, preventing a 5.

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