merge_policy

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

With no annotations, the description must carry the behavioral disclosure. It honestly states the get/set duality and the no-args read behavior. However, it does not disclose side effects of setting thresholds, whether partial updates are allowed, or what a set call returns. This is adequate but not deeply transparent for a mutation-capable tool.

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, front-loaded with the verb and resource, and no filler. The special no-args behavior is included efficiently.

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 config getter/setter, the description covers the resource and read path, but it leaves ambiguity about partial vs full replacement when setting only one parameter, does not describe the return shape of a set or get call, and does not mention any validation relationship between the two thresholds. These are meaningful gaps for correct invocation.

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 baseline is 3. The description adds the 'Fellegi-Sunter' domain context and names the fields, but most parameter meaning already exists in the schema. It does not materially extend the schema's descriptions.

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 uses a specific verb phrase, 'Get or set', a concrete resource, 'the per-project merge policy', and names the three settings. It is clearly distinct from the merge execution siblings like plan_merge and apply_plan because it focuses on configuration rather than operations.

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: call with no args to read the policy, call with args to change it. However, it does not explicitly distinguish it from related merge-family tools or state when not to use it, leaving the agent to infer the boundaries from the resource name.

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