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

Annotations already declare this a safe read (readOnlyHint=true, destructiveHint=false, openWorldHint=false), so the bar is lower. The description goes beyond them, disclosing what is returned in each mode (persisted pre/post scored cohorts, model IDs, score definition, cost delta) and the notable constraint that model swaps work 'without requiring an issue index'.

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?

Four sentences, front-loaded with the core purpose before mode-specific detail and example queries. Dense but every sentence carries signal; no filler or restatement of the title.

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?

With no output schema, the description carries the return-value burden and does so by naming the payloads for both modes. The superadmin-only customerId is only covered by the schema, not the description, which is a minor gap for a 3-param tool.

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 baseline is 3. The description adds conditional semantics that the schema does not: issueIndex is unnecessary for model swaps but is required alongside deploymentId for prompt fixes. This meaningfully guides parameter combination beyond the flat per-parameter text.

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 and resource: 'Show the actual runs behind a verification claim.' It clarifies the two distinct modes (model swaps vs. prompt fixes), which separates it from generic run lookups like get_run. It never names a sibling alternative directly, so it stops short of full differentiation.

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?

Provides clear contextual triggers, including the phrasing 'show me the proof', 'which runs had this issue?', and 'back up this claim'. It also ties usage to input combinations (model swaps need no issue index; prompt fixes need deployment ID + issue index). It does not state when to prefer an alternative tool or any exclusions.

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