proofrelay.verify_bundle

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

Annotations already mark readOnlyHint=true, destructiveHint=false, idempotentHint=true. The description adds beyond that: 'does not certify real-world facts' and 'returns JSON text with status, checks, problems, verifier, and hosted endpoint fields,' which neither contradicts annotations nor repeats them. It gives the agent concrete behavioral expectations.

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?

Two sentences, no fluff. First sentence delivers purpose and usage; second adds behavioral constraints and output format. Every phrase earns its place, and critical info (safety, authentication, alternative) is front-loaded.

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?

Given the tool has one parameter (nested object), output schema exists, and annotations are rich, the description still adds value: it explains what the tool does not certify, gives output field names, and distinguishes from siblings. No gaps remain for an agent to make incorrect assumptions.

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?

The only parameter 'bundle' has schema coverage 100% with a description that lists what to include ('Synthetic or non-confidential evidence bundle metadata') and explicitly warns what NOT to include ('Do not include secrets, prompts, raw logs, source code, customer files, wallet keys, payment credentials, or tenant traces'). The tool description reinforces this, adding no redundancy.

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 starts with 'Read-only public-safe bundle shape check for synthetic or non-confidential evidence metadata,' clearly stating the verb (check), resource (bundle), and scope (synthetic or non-confidential). It also distinguishes from sibling 'recommend_checkpoint' by name, ensuring no ambiguity.

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 explicitly states when to use this tool: 'when you already have a bundle fixture and need a local pass/fail boundary check before sharing or routing to hosted verification' and provides a clear alternative: 'use recommend_checkpoint when deciding whether a checkpoint is needed.' It also notes 'Requires no authentication, mutates nothing,' guiding safe usage.

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