watch_workflow

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

Annotations already declare readOnlyHint=true, so safety is covered. The description adds genuinely useful context — the returned result includes failed logs and defaults to release.yml at HEAD — but says nothing about the running/terminal states, polling expectations, or auth requirements that matter for a watch tool.

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?

It is a single short sentence with no waste, but the sentence-fragment structure and the awkwardly placed parenthetical make it harder to parse than it needs to be. Brevity here shades into under-specification rather than efficiency.

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 and a polling tool whose return value varies by run state, the description should explain what comes back and how to handle a still-running result. Instead it gives one clause about failed logs and leaves the required dir parameter and the running state unexplained.

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 50%: ref, workflow, and waitSeconds are documented in the schema, and the description reinforces the HEAD/ref and release.yml/workflow defaults. However, the one required parameter, dir, is undocumented in both the schema and the description, which is a notable 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 names the resource (a workflow run for HEAD, default release.yml) and mentions failed logs, but it is a noun phrase with no verb — an agent cannot tell whether it triggers, polls, or merely fetches results. It also does not distinguish itself from the sibling job_status, which plausibly covers overlapping ground.

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 statement of when to use this tool, when not to, or which sibling to prefer. The polling behavior is only hinted at by the schema's waitSeconds text ('call again while running'), leaving the description with no routing guidance at all.

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