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

The description goes well beyond the readOnlyHint annotation by revealing the literal return behavior: the file contents are returned as text, not as a pointer or attachment. It also explains the non-obvious semantic difference between CSV and JSON, including tenant-specific JSON keys, which is exactly the kind of behavior an agent cannot infer from the schema.

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 front-loads the most important constraint ('COMPLETED') and then spends every sentence on functional distinctions that affect agent decisions: success state, format semantics, and return shape. There is no filler or repetition of the schema's plain parameter descriptions.

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 tool with no output schema, the description compensates well by stating that the result is returned as text and explaining what the text contains per format. It still leaves some ambiguity about exact JSON/CSV structure and error handling for nonexistent jobs or bad job IDs, but an agent can decide whether to call it confidently.

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 coverage is 100%, so the baseline is 3, but the description adds real meaning to the format parameter by explaining exactly what each format contains and by warning that JSON is not a superset of CSV. It does not add much about how to obtain a jobId, but the schema and context make that secondary.

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 a specific resource, a 'COMPLETED window replay job', and a clear action, export, while adding the state qualifier that distinguishes it from still-running jobs. This is far more specific than the title alone and separates it from export tools for simulations or facts.

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 clearly tells the agent to export only completed jobs and explains that running jobs are rejected, with the underlying reason. It also gives concrete guidance on choosing CSV versus JSON based on what each format contains. It stops short of naming an explicit alternative for non-replay exports, so it earns a 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.