bridge_scope

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

With no annotations supplied, the description carries the full behavioral burden, and it discloses almost nothing. It does not say that claim is a mutating, conflict-prone operation, whether a held lease blocks the claim, what happens on expiry, whether release requires the original owner, or whether any of this needs authorization. Only the bare existence of leases is conveyed.

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?

One sentence, front-loaded with the verbs, with no filler or repetition. However, the brevity is achieved through under-specification rather than economy — the same sentence could have carried the claim-before-edit rule without becoming bloated.

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?

This is a stateful, mutating coordination tool with six undocumented parameters, no annotations, and no output schema. The description gives no sense of the lifecycle (claim to release), failure modes, or what a list result contains, so an agent would have to guess at every non-trivial call.

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% across six parameters, so the description must compensate and does not. It never explains `globs` (what path patterns are covered by a lease), `ttl` (format or expiry behavior), `lease_id` (required for release?), `reason`, or `all` (scoping list to all worktrees?). Only the `action` enum values are echoed in prose.

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 three concrete verbs (claim, release, list) applied to a specific resource (cross-worktree file scope leases), and the verb set maps exactly onto the `action` enum, so an agent can match intent to tool. It loses a point because 'file scope lease' is domain jargon with no gloss, and it draws no boundary against the sibling bridge_* tools, leaving the agent to infer that this is the only concurrency-control tool in the family.

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 when-to-use guidance at all: nothing says an agent should claim before editing shared files, release when done, or list to discover existing holders. The three modes are enumerated but the conditions that select among them are left entirely to inference, and there is no mention of what to do when a claim is refused.

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