get_report

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds one genuinely useful behavioral fact — the fallback to the last successful run when run_id is absent — but says nothing about report size, freshness, or what 'successful' means.

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 short sentence with no filler, and the default behavior is placed in the natural spot. It is however a sentence fragment with no leading verb, and it is arguably under-specified rather than appropriately concise for a retrieval tool.

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 two optional parameters, no output schema, and no nested objects, the definition could easily be complete — but it never says what a 'report' contains, how env affects the result, or how this differs from list_reports and audit_report. The agent can invoke it, but cannot confidently predict what comes back.

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 only 50% and run_id has no schema description at all; the description supplies that meaning by framing it as the selector for a specific run and defining the omission default. It does not explain what a run_id looks like or how env interacts with it, but it carries the main semantic load for the undocumented parameter.

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 the resource ('a full report') and implies retrieval, which is clearer than the bare name get_report. But it is a noun phrase with no verb and gives no basis for choosing it over siblings like list_reports or audit_report, so an agent must infer the distinction.

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 only usage signal is the conditional 'the last successful one if run_id is omitted', which tells the agent what happens by default but not when to prefer this tool over list_reports or audit_report. There are no exclusions and no prerequisites stated.

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