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

Annotations already declare readOnly, idempotent, and non-destructive behavior. The description adds valuable operational detail—return values of 'complete' vs 'running' with elapsed time, plus readiness for report download—while staying consistent with the annotations.

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 efficiently packs purpose, required input, status values, polling cadence, and expected completion time into a compact block. The generic when-to-use/when-not-to-use sentences add some filler, but they do not meaningfully hurt readability.

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 single-parameter polling tool with readOnly/idempotent annotations and an output schema, the description fully covers how to call it, what statuses to expect, and how long to wait. Nothing an agent needs to invoke and interpret the result is missing.

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%, and the schema already describes audit_id as 'returned by ghost_audit_site.' The description repeats that provenance without adding format, validation, or additional semantic detail, so it meets the baseline but adds no new parameter meaning.

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 a specific verb-object pair—'Check the status of a running Ghost Audit'—and makes the tool's purpose unmistakable. The running-to-complete status transition also clearly separates it from related tools like ghost_audit_site and ghost_audit_report.

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 concrete guidance: require audit_id from ghost_audit_site, poll every 15-30 seconds, and expect 60-120 second completion. The 'when not to use' clauses are present but generic and do not name a specific alternative, so it stops short of fully explicit routing.

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