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

Annotations already declare readOnlyHint=false and idempotentHint=true, so the mutation/idempotency profile is covered. The description adds real behavioral context beyond that — the gated merge chain, that the arm persists while pending, that `last_attempt.reason` reports the blocker, and the write-access/'repo' scope requirement. However, it arguably undersells that disarming is not harmless (it can hold a PR out of the train), and the 'destructiveHint: false' framing plus the partial return disclosure keeps this from being fully transparent.

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?

Front-loaded with the verb pair and the returned shape, then progressively adds the gating chain, the train semantics, and permission requirements — a sensible ordering. It is dense rather than padded, but the repeated 'merge_method: merge only' clause duplicates schema content and the multi-clause sentences are long enough to slow scanning slightly.

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 mutating tool with five parameters and no output schema, the description covers the essentials: what gets armed, what the armed state waits on, how to inspect the blocker via `last_attempt.reason`, permission/scope prerequisites, and the return shape `{number, auto_merge}`. Nothing critical is left to inference.

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 100%, so both `enabled` ('true = arm, false = disarm') and `merge_method` ("'merge' (default; the only method the gated chain has)") are already documented in structured fields. The description's main contribution is the behavioral consequence of `enabled`, but it restates the merge_method restriction verbatim rather than adding new semantics. Baseline 3 is appropriate given the schema does the heavy lifting.

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?

Opens with a concrete verb pair (arm/disarm) and a precisely scoped resource: auto-merge on exactly one PR, with the meaning of the `enabled` flag stated inline. It is clearly distinct from sibling gluecron_merge_pr, which it names as the explicit-merge alternative, so an agent can choose between them without opening either schema.

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?

Gives explicit when-to-use semantics: arming is the merge train's consent, disarming holds the PR from the train, and an explicit gluecron_merge_pr still merges. It also states the conditions under which the armed state actually fires (CI and all required checks green, no changes requested by a write-access reviewer), which is exactly the decision context an agent needs.

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