run_release_check

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

With no annotations, the description carries the full burden. It discloses important behaviors: returns a decision, queues asynchronously in replay mode, runs synchronously in targeted mode, and smoke_preflight is advisory and non-blocking. It also explains the deprecated alias. However, it omits potential side effects like whether runs are persisted or if specific permissions are required.

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?

The description is well-structured, front-loading purpose and then breaking down modes and arguments clearly. It is appropriately sized for the tool's complexity, with each line adding useful information. The deprecated alias note is valuable but adds a bit of length.

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?

While the description covers the main modes and return types (decision, run_id), it leaves gaps for a tool of this complexity. The required app_url is not mentioned, and there is no output schema to fall back on. The behavior of headless, run_mode, and profile_name is undocumented, making the description incomplete for full understanding.

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 0%, so the description must explain all parameters. It explains several (journey_ids, flow_ids, criticality_filter, release_id, mode, smoke_preflight) but completely misses app_url (the only required parameter), headless, run_mode, and profile_name. Additionally, the stated default for criticality_filter (['revenue','activation']) conflicts with the schema's null default, adding confusion.

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 clearly states the tool's purpose: 'Flagship release confidence tool: replay critical journeys and return a SHIP / INVESTIGATE / BLOCK decision.' This specifies the verb (replay), resource (critical journeys), and outcome (decision), distinguishing it from sibling tools by its central role in release gating.

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?

It clearly describes the two modes (replay and targeted) and when each is appropriate, positioning replay as the 'golden path for release gating' and targeted as a 'shortcut smoke check.' However, it does not explicitly mention alternative sibling tools or state when not to use this tool.

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