Remove Evidence

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

With no annotations, the description carries the burden and explicitly states 'Mutating.' It also discloses the non-effects (does not affect implementation status or assertions), which is valuable behavioral context beyond the obvious delete action. It does not mention error behavior on an invalid index or reversibility, but the core consequences are covered.

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?

Three sentences, each serving a purpose: the action, the consequence, and the how-to-find-the-index. The key term 'Mutating' is front-loaded, and there is no fluff or repetition of schema content.

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 simple removal tool with 4 parameters, an output schema, and no annotations, this description is complete enough to call correctly. It explains what is removed, what is unaffected, and exactly how to determine the evidence_index. The only unannotated parameter is server_version, but the schema coverage is high and output schema is present, so the description need not fill that gap.

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 descrition coverage is 75%, so the baseline is 3. The description reinforces the zero-based indexing and references get_controls for finding the index, but the schema already documents evidence_index with 'Zero-based position' and a default. The description adds little new parameter meaning beyond what the input schema provides.

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?

States a specific verb ('Remove'), resource ('one evidence item from a control'), and method ('by its position in the control's evidence array'). This clearly distinguishes it from add_evidence, get_controls, and other siblings by defining both the action and the targeting mechanism.

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?

Gives clear context: evidence is auxiliary metadata, removal does not affect status or assertions, and the way to find the index is to read the control via get_controls. This is actionable guidance, but it does not explicitly list when-not-to-use or directly compare against a sibling alternative beyond referencing add_evidence.

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