bridge_fail

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

Beyond what annotations already convey (mutation, non-idempotent), the description discloses the full state machine behavior: a failed task is requeued after retry_delay_seconds until max_attempts is exhausted and then dead-lettered. It also exposes the immediate dead-letter path (requeue=false) and the lease_token prerequisite — all operational behaviors the agent cannot infer from the annotations or schema. The description is consistent with annotations; no contradiction.

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 two sentences with no filler, front-loaded with the action verb. The second sentence efficiently captures the default retry behavior, the terminal dead-letter outcome, the immediate-path alternative, and the required resource. Every clause adds necessary behavioral information.

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 an output schema present, return-value explanation is unnecessary. The description covers the complete contract of this tool: the state transition, the retry/dead-letter timeout behavior, the forcing path to immediate dead-letter, and the token prerequisite from bridge_claim. Nothing missing that an agent needs to invoke this tool correctly within the bridge task lifecycle.

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 only 17%, so the description shoulders the explanatory load. It meaningfully explains the critical parameters: requeue (false => immediate dead-letter), retry_delay_seconds (the retry wait), and lease_token (source and meaning). The remaining parameters (channel, task_id, error) are left implicit — task identity is clear from the 'claimed task' context and the schema already describes error — so the compensation is strong but not exhaustive.

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 opens with the direct action 'Mark a claimed task failed,' which names the verb and resource clearly. It further differentiates this operation from the task-lifecycle siblings by spelling out the failure path (requeue/dead-letter), making it easy to distinguish from complementary tools like bridge_ack and bridge_complete.

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?

The description gives a concrete and important prerequisite — 'Requires the lease_token from bridge_claim' — which tells the agent exactly when in the workflow this tool is valid. It also spells out the two usage paths (default requeue vs. requeue=false for immediate dead-letter), but it does not explicitly name the alternative tools (e.g., 'use bridge_complete when the task succeeded'), so the when-not guidance is implicit rather than stated.

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