Tower runbook_recommendations

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

Beyond the readOnlyHint annotation, the description discloses two genuinely useful behavioral traits: returned evidence is untrusted data requiring record-ID citation and preserved uncertainty, and the tool does not perform human approval or execution (that path lives in Tower HTTP/CLI). This meaningfully extends the safety profile the annotations already declare, though it still says nothing about the shape or ordering of the recommendations returned.

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 sentences with no bloat, and the untrusted-evidence constraint is stated up front. However, the leading sentence is pure filler that repeats the tool and title instead of defining what the tool does with the incident ID.

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 one-parameter read-only tool with no output schema, the description covers the trust/approval boundaries but omits the core contract: what a "recommendation" contains and how the incident ID drives it. An agent could call it, but could not predict the result or set expectations for the user.

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% for the single required parameter, and the description never mentions incident_id — no format, source, or whether it must come from tower.incidents. With one undocumented required parameter, the description does not compensate for the schema gap.

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 essentially restates the tool name ("runbook_recommendations") inside an "Authenticated Control Tower" wrapper and never states a verb or object, e.g. "recommend runbooks for a given incident." It does not distinguish this tool from close siblings such as tower.runbooks, tower.runbook_preview, or tower.incidents, so an agent must infer the actual function.

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?

There is no explicit when-to-use guidance, no exclusions, and no routing to alternatives among the many tower.runbook_* siblings. The only scope hint is indirect — that human approval happens "separately" via Tower HTTP/CLI — which implies this tool is advisory, but not when to pick it over tower.runbooks or tower.runbook_preview.

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