Edit Evidence

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

With no annotations, the description carries the full burden and largely meets it: it declares the operation mutating and, more valuably, states the non-effect of removal on status and assertions - a semantic trait an agent could otherwise guess wrong. It still omits permission requirements, whether edits are auditable/undoable, and any failure modes.

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?

Purpose is front-loaded in the first sentence, followed by a one-word mutation flag, then the semantic caveat. The caveat is slightly restated twice ('removing it changes neither the status nor any assertion' / 'Only assertions prove controls'), but both sentences carry distinct weight and nothing is padded.

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?

Eight parameters at 88% schema coverage plus an output schema mean structured fields handle details; the description supplies exactly the missing conceptual layer - that this is a mutation of contextual metadata with no effect on control implementation status - which is what an agent needs to decide whether to call it.

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 88%, so the schema already documents the action enum, item type values, and the zero-based evidence_index. The description adds only a high-level gloss (attach vs detach, what an item is), which is marginal beyond the structured data, so baseline 3 is appropriate.

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 concrete verb pair (attach/detach), the resource (an auxiliary evidence item), the item kinds (doc, link, artifact reference), and the parent object (a control). The closing line distinguishes evidence from assertions, which is exactly the boundary that separates this tool from assertion-oriented siblings in the list.

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 statement that evidence 'does NOT count toward a control's implementation status' and that 'only assertions prove controls' implicitly tells the agent when this tool is appropriate versus proof-bearing tools. However, there is no explicit when-to-use rule, no prerequisite call chain (e.g., read evidence_index via get_controls before removing), and no named alternative.

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