remove_evidence

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

With no annotations provided, the description carries the burden of behavioral disclosure. It states 'Mutating.' and clarifies the side effect—'does not affect the control's implementation status or any assertions.' This goes beyond the basic action to explain non-impact. However, it doesn't mention error conditions, idempotency, or whether the removal is reversible, which would add completeness. Still, the key mutation behavior and its limited scope are well disclosed.

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 concise and front-loaded: the first sentence states the core action, and the second paragraph provides essential usage and side-effect context in two sentences. No redundant or fluff content. It reads efficiently and every sentence adds value.

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's simplicity, the rich input schema (with descriptions for 3/4 params), and the presence of an output schema (so return values are not needed), the description provides sufficient context. It explains the mutation's limited impact, how to find the index, and refers to related tools (add_evidence, get_controls), making it complete for an agent to use correctly.

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 75% (only server_version lacks a description). The description enhances understanding of evidence_index and control_id by explaining how to locate the index—'count its evidence array from 0'—and by specifying the array is zero-based. This adds meaning beyond the schema's default description. It doesn't elaborate on server_version, but the high baseline coverage plus the added context justifies a 4.

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 explicitly states: 'Remove one evidence item from a control by its position in the control's evidence array.' This uses a specific verb (Remove), a specific resource (evidence item from a control), and a precise method (by position). It distinguishes itself from sibling add_evidence and delete_control by focusing on a single evidence item without affecting the control itself.

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 provides clear guidance: it explains that evidence is auxiliary metadata and removing it does not affect implementation status or assertions, implying when it's safe to use. It also gives explicit steps to find the index: 'read the control via get_controls (control_id=...) and count its evidence array from 0.' This addresses when and how to use the tool, contrasting with alternatives like add_evidence.

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