Hedgehog

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

With no annotations provided, the description carries the full burden. It discloses the 0-100 range constraint and implies persistence ('Record'), but omits details about side effects, idempotency, error conditions (e.g., non-existent spike), or storage behavior.

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?

Well-structured with purpose first, constraints second, and pseudo-docstring Args section efficiently covering parameters. No redundancy, though the Args list slightly lengthens the text it is necessary given zero schema descriptions.

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 6 parameters with 0% schema coverage, the description adequately documents all inputs. With an output schema present, omitting return value explanation is acceptable. Missing only behavioral side-effects and explicit sibling differentiators.

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 coverage is 0% (only titles), requiring description to compensate. The Args section documents all 6 parameters with clear semantics (e.g., 'How well is the problem understood (0-100)'), fully compensating for the sparse schema though lacking rich examples or deep constraints.

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 'Record[s] a confidence rating for the spike' with specific verb and resource. It distinguishes itself from sibling spike tools by focusing specifically on confidence metrics and evolution tracking.

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 phrase 'Tracks confidence evolution over time' implies temporal usage (periodic reassessment), but lacks explicit guidance on when to use this versus alternatives like spike_checkpoint or spike_complete_branch, and doesn't state prerequisites.

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