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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safe-read profile is covered. The description's contribution is naming the payload fields (status, report_markdown, sources, fix_report), which is genuinely useful given there is no output schema, but it says nothing about progress/terminal states or polling cadence.

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?

A single front-loaded line with no filler, and the returned-field list is packed efficiently. The fragment style and the unexplained term 'fix_report' make it slightly cryptic rather than maximally clear.

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 no output schema, listing the returned fields is the right move and partially fills that gap. Still missing are the completion/terminal-state semantics and the origin of job_id, which an agent needs to poll correctly rather than guess.

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?

There is a single parameter (job_id) with 0% schema description coverage, and the description does not mention it or say where the id comes from (presumably create_snapshot). The field list compensates slightly by describing what comes back, but parameter meaning is left entirely to the identifier's self-evident name.

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 uses a specific verb ('Poll') plus a specific resource ('a Competitor Snapshot') and enumerates the returned fields, so an agent knows this checks the state of an existing snapshot. However, it never distinguishes itself from the sibling get_job_status, which by name appears to be a very close alternative, leaving the boundary to inference.

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?

'Poll' implies repeated invocation until the snapshot is ready, which is a usable hint about when to call it. But there is no explicit statement of when to stop, what terminal states look like, or why an agent would pick this over get_job_status, so the guidance is only implied.

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