analyze_gaps

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

The annotations already cover readOnly, idempotent, and destructive hints. The description adds a notable behavioral detail: that it 'reports gaps to ADR Aggregator for tracking', which is not captured in the annotations. This extra context informs the agent about a potential side effect (external reporting) beyond the annotated read-only nature. However, it does not elaborate on the reporting mechanism or any permissions implied, so it is not fully transparent.

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 concise and well-structured. It opens with a clear one-sentence summary, then breaks down the two gap types into bullet-like numbered points, and ends with the reporting behavior. There is no redundant or verbose language, and every sentence earns its place.

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?

The description lacks information about what the tool returns to the caller. It mentions 'reports gaps to ADR Aggregator' but does not state whether the tool returns a list, a summary, or any direct output to the invoking agent. Since there is no output schema, the description should at least specify the return format or indicate that no direct output is provided. This omission leaves the agent uncertain about the tool's immediate effect and return value.

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 provides descriptions for all 6 parameters, covering 100% of them. The tool description itself does not add any extra meaning or context for the parameters; it relies entirely on the schema. Since schema coverage is high and the descriptions are adequate, the baseline score of 3 is appropriate.

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's purpose: it scans the codebase and compares with ADRs to detect two specific types of gaps (ADR-to-code and code-to-ADR). This is a specific verb (scan, compare, detect) tied to a specific resource (local codebase and ADRs), and the two gap types are explicitly enumerated. It distinguishes itself from siblings like 'get_gaps' (which likely retrieves gaps rather than analyzing them) enough for an agent to choose it correctly.

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 does not explicitly state when to use this tool instead of alternatives. It implies the use case (finding gaps), but there is no mention of conditions like 'when you need a fresh analysis' or 'to retrieve existing gaps use get_gaps'. The description is functional but not prescriptive about scenarios or comparisons with sibling tools.

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