log_learning

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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the write-safe profile is covered. The description adds one genuine behavioral constraint not in annotations: writes require project=<name> or project_id. It says nothing about deduplication, validation failures, or what happens to learnings after capture.

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?

Three short sentences, front-loaded with the core action and the critical project requirement. 'This is your memory - use it!' is motivational filler but takes little space.

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?

No output schema exists, and the description does not need to cover return values. But for an 8-parameter tool at 50% schema coverage with no annotation detail on mutation effects, the description leaves the classification parameters (category, source) and the model/component_id fields unexplained.

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?

With 8 parameters and only 50% schema description coverage, the description compensates partially by clarifying the project/project_id requirement, which the schema's required array omits. However, it adds nothing for category, source, context, model, or component_id, leaving several parameters documented only by enum values or not at all.

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?

States a specific verb+resource combination ('Capture an insight or learning') that an agent can immediately map to a write operation. It does not explicitly name its read counterpart get_learnings, so sibling differentiation is left to inference.

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?

'This is your memory - use it!' gives a soft nudge toward use but no when-not conditions and no comparison to alternatives like log_change or log_work. The prerequisite (project required for writes) is stated, which is the most actionable guidance present.

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