calibrate_threshold

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

It discloses the sampling mechanism, the placement of the threshold above the null mean, the three statistical methods, and the absence of label usage, which goes well beyond the sparse annotations. It does not detail persistence or failure conditions, but the annotations already signal a non-read-only, non-idempotent operation.

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 purpose is front-loaded and the method explanations are technically dense, but they duplicate some of the schema's method description. The overall paragraph is efficient and well structured, with only minor redundancy preventing a 5.

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 5-parameter mutating tool with no output schema, the description covers methodology and method selection well but omits the expected return value or whether the calibrated threshold is persisted. Given that annotations and output schema are thin, these are meaningful gaps.

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%, so the baseline is 3, but the description adds meaning: it explains the zscore formula, says percentile is robust to anisotropic embedding models, and ties methods to null-pair populations. This helps an agent choose between methods beyond the schema's parameter 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 opening sentence states a concrete action ('auto-calibrate') applied to a specific resource ('vector search threshold'), and the method breakdown makes the tool's scope obvious. This distinguishes it from sibling tools like set_recall_precision or get_recall_precision without needing schema inspection.

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 appropriate use through phrases like 'no labels used' and 'adapts to both embedding model and corpus characteristics', but it never explicitly says when to prefer this over manual threshold setters such as set_recall_precision. There is clear context, but no when-not-to-use or alternative routing.

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