set_recall_precision

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

Annotations declare idempotentHint=true and destructiveHint=false, and the description aligns with this: setting precision is idempotent and not destructive. The description adds valuable behavior: effect is immediate and persisted without restart, and the gate is precomputed on the separation curve, meaning the change is live. It also clarifies the override-clearing side effect, which is important behavior. Minor, but it could have explicitly stated that no confirmation or output is returned, given no output schema, so a 4 is appropriate.

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 dense and packed with essential information, but it is a single long paragraph. It front-loads the core purpose and immediately explains the main knob, but the second sentence is quite long and mixes multiple concepts (mapping, formula, override, default). It could be broken into shorter sentences for readability, but every sentence earns its place. A 4 is fair.

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 that this is a simple configuration tool with 3 parameters, 100% schema coverage, no output schema, and annotations covering idempotency/destructiveness, the description is complete. It explains what happens immediately, how the override works, when to use which mode, and the relationship to the global default. Nothing essential is missing.

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 100%, and the schema descriptions are already clear (e.g., beta raw override, precision enum, agent_id). The description adds mapping of the three named levels to specific beta values (2.0/1.0/0.5) and the formula, which goes beyond the schema, but the core parameter roles are already well-documented. So a 3 is fair.

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 states a specific verb (set/recalibrate), a clear resource (agent's recall precision, 'knob 3'), and immediately defines the three levels plus the beta semantics. Even though the sibling set includes get_recall_precision and calibrate_threshold, this description's emphasis on per-agent precision versus per-recall arguments and its mention of 'recalibrates once' distinguishes it from the threshold-calibration sibling.

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 explicitly explains when to use the named level (strict/balanced/lenient maps to beta), when to use a raw beta override (beta > 0), and when to clear the override (empty precision with beta <= 0 returns to the global default). It also states that precision is a per-agent setting, not a per-recall argument, which implicitly distinguishes this tool from recall-related siblings. This is near-explicit guidance.

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