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

Annotations already cover the safety profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false, openWorldHint=true), so the description adds the substantive side effect: it records the added/removed/revised evidence deltas resulting from the run. That is meaningful behavioral context beyond the annotations, though auth needs and whether it triggers retrieval are unstated.

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?

A single front-loaded sentence with the verb and result stated immediately and zero filler. Nothing is padded or redundant.

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 low-complexity, one-parameter mutation tool with annotations covering safety, the description is roughly adequate on behavior but thin on sourcing the required watch_id and on when this run should be invoked versus its siblings. No output schema exists, so return values would need coverage, which is absent.

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?

The single parameter watch_id has 0% schema description coverage, and the description never explains where watch_id comes from (e.g., list_evidence_watches or create_evidence_watch) or its expected format. With one undocumented parameter in both schema and description, the meaning is not conveyed.

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 pairs a specific verb ('Run') with the resource ('one evidence watch') and states the outcome ('record added, removed, or revised evidence'). The word 'one' implicitly distinguishes it from the sibling run_all_evidence_watches, but neither that sibling nor create_evidence_watch is named, so differentiation is left to inference.

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?

Usage is only implied: 'one' suggests a single targeted watch versus run_all_evidence_watches, but the description never states when to use this instead of creating or listing watches, nor any prerequisites for the watch_id. No explicit when/when-not guidance is present.

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