Verify Execution Evidence

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

Annotations only declare readOnlyHint=true; the description adds real behavioral detail beyond that, namely that keys come from the host configuration (so no credential parameter is needed), that raw payloads are deliberately omitted from the response, and that only verification, coverage and causal IDs are returned. That is useful disclosure for an agent reasoning about what output to expect, though it says nothing about what happens on a failed or partial verification.

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 short, front-loaded sentences with no filler; the most decision-relevant facts (what it verifies, no raw payloads, no execution) come first. The final "No execution" fragment is slightly redundant with readOnlyHint but still earns its place as a scope guard.

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?

The description does name the response contents (verification, coverage, causal IDs), which partly compensates for the missing output schema. However, for a tool taking an opaque nested "bundle" object with zero schema documentation and no output schema, the definition leaves the agent unable to construct a valid call without guessing.

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 0% and one of the two parameters is an untyped nested object, yet the description never explains what belongs inside "bundle" (traces? artifacts? manifest?) or what run_id must match. The description adds no meaning beyond the schema's bare names, which is a serious gap given the nested-object complexity.

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 ("Verify") and a specific resource ("Lens AIOS execution bundle"), and adds that verification uses host-configured keys. It does not explicitly differentiate itself from look-alike siblings such as core.verify, tower.verify or tower.runbook_verify, so an agent must infer the distinction from the phrase "execution bundle".

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?

"No execution" is a mild exclusion and hints that this is a safe check-only path, but there is no positive guidance about when to pick this over core.verify, tower.verify or lens.diagnose_run, nor any prerequisite or precondition described. The agent must infer selection from the tool name alone.

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