generate_reconciliation_prompt

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

The annotation readOnlyHint:true already informs the agent that this is a safe, non-mutating operation. The description adds that it 'produce[s] a structured LLM-ready prompt,' clarifying the output type but does not disclose other behavioral traits such as whether it requires specific permissions, handles errors from missing notes, or has any side effects. Given the annotation covers the safety aspect, the description adds moderate value.

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 that is front-loaded with a clear verb and resource. It contains no unnecessary words and effectively communicates the tool's purpose. Every part earns its place, making it concise and well-structured.

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 the tool has 2 parameters, a read-only annotation, an output schema, and siblings, the description is incomplete. It does not describe the parameters' formats or expected values, nor does it explain what the 'LLM-ready prompt' looks like (though the output schema might cover that). The agent lacks sufficient context to confidently invoke the tool without additional assumptions.

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 0%, so the description must compensate. It mentions 'two notes' and uses note_a_path and note_b_path, implying these are paths to notes. However, it does not elaborate on the format, constraints, or examples of valid paths. The high-level context is provided, but deeper detail is absent, limiting the agent's ability to construct correct inputs.

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: 'produce a structured LLM-ready prompt for reasoning through the conflict and suggesting resolution.' The verb 'produce' and the resource 'structured LLM-ready prompt' are specific. It distinguishes from siblings such as 'find_contradictions' and 'check_pair' by focusing on generating a reasoning prompt rather than detecting or checking contradictions.

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 usage context with 'For a detected contradiction between two notes,' indicating it should be used after a contradiction is found. However, it does not explicitly state when to use it versus alternatives like 'extract_claims' or 'check_pair,' nor does it provide any exclusions or warnings. More explicit guidance would improve decision-making.

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