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

Annotations provide openWorldHint=true and destructiveHint=false, and the description adds the context of 'existing authorization' and that a corrected destination may be supplied. It does not contradict annotations. However, it does not describe side effects beyond queueing an attempt, nor does it clarify whether the original failed fax is altered or if any rate limits apply. With minimal annotation coverage, the description adds some value but leaves behavioral details underexplained.

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 with no redundant phrasing. The first sentence front-loads the usage condition and core action, and the second adds the optional input. Every word earns its place; it is tight and easy to parse.

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?

The description tells when to use the tool but does not explain how to identify which failed fax to retry (e.g., whether sendIntentId or sessionId is required or how they relate). It mentions 'existing authorization' but not that either identifier must be passed. Given there is an output schema (not provided but signaled) and 3 optional parameters, the description could be more explicit about the required inputs for a retry. This is a notable gap for a tool that depends on prior state.

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 each parameter already has a description. The tool description adds the phrase 'corrected destination' which restates the schema's 'Optional corrected US fax number' without adding new meaning. It also implies that authorization is tied to existing session or intent IDs, but this is already in the parameter descriptions. Overall, the description adds minimal value over the schema, so a baseline 3 is appropriate.

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 clearly states the tool's specific purpose: 'retry a retry-eligible failed fax' and 'queue another attempt under the existing authorization'. The verb 'retry' and resource 'failed fax' are specific, and it distinguishes from siblings like send_fax (new sends) and cancel. The condition 'after a retry-eligible failed fax' adds precision, making it unambiguous what this tool does.

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?

It provides an explicit when-to-use condition ('after a retry-eligible failed fax') and clarifies that it operates under existing authorization. It does not explicitly name alternatives or say 'do not use for new sends', but the context implies it is distinct from send_fax and other operations. A sibling comparison would strengthen it, so it's a strong 4 rather than a 5.

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