resolve_error

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

No annotations are provided, so the description carries the full burden. It usefully discloses the state file it mutates and the non-obvious behavior that a recurring error auto-reopens, but omits permissions, behavior when the error_id is unknown, and any confirmation/return semantics.

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?

Two sentences, zero filler, and the core mutation is front-loaded with the auto-reopen caveat following immediately.

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 simple two-parameter mutation with no output schema, the description covers the action, its target state, and the important reversibility nuance. Only edge cases (unknown error_id, the 'project' parameter) are left unaddressed.

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 both parameters are already documented, including the omit-all behavior. The description restates that behavior without adding format or constraint detail, matching the baseline for high-coverage schemas.

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 ('marks ... as resolved') and resource ('error_id'), plus where the change lands ('.agentsensor/status.json'). It clearly isn't a read tool like the get_* siblings, though it doesn't name the alternatives explicitly.

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 when to use it (after fixing an error) and clarifies the omit-to-resolve-all case, but gives no explicit when-not guidance or comparison to check_fix, which an agent might reasonably confuse this with.

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