save_attempt_note

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

Annotations already indicate a write operation (readOnlyHint: false) but provide no additional detail. The description adds only the ambiguous word 'restartable', which may hint at checkpointing but is not explained. It does not mention the required lease_token proof, potential side effects, or any idempotency nuances (despite the idempotency_key parameter). This leaves significant behavioral gaps.

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 a single sentence and is very concise with no filler. It front-loads the action. However, 'restartable' is unclear and might mislead; a slightly more explicit phrase like 'save an attempt note that can be used to resume work' would be both concise and clearer. Still, it earns a high score for structure.

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 tool with 10 parameters including sensitive auth fields (lease_token), idempotency control, and an enum, the description is too thin. It does not explain the lease requirement, the meaning of 'restartable', or how the different note kinds should be used. The output schema exists, so return values are not necessary, but the high-level operational context is missing.

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 description coverage is 100%, so the schema itself documents all parameters with descriptions. The tool description adds no parameter-specific meaning beyond 'restartable', which does not map to any one schema field. The baseline of 3 is appropriate since the schema carries the burden.

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 ('Append'), the resource (a note to an attempt), and the scope (checkpoint, finding, warning, or progress). It distinguishes from sibling tools like add_comment or record_decision by referencing attempt-specific notes. Though 'restartable' is slightly vague, the core purpose is unambiguous.

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?

No guidance is provided on when to use this tool versus alternatives. There is no mention of prerequisites (e.g., active attempt lease), when to choose 'checkpoint' vs 'progress', or situations where another tool like record_decision might be more appropriate. The description is a bare statement with no exclusions or contextual hints.

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