Best AI Search Agency AEO Report

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

Annotations only declare readOnlyHint and openWorldHint; the description adds the real behavioral payload: the full status enum split into in-progress vs terminal, and what each terminal branch returns. Missing only operational details like rate limits or poll 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?

Front-loaded with the action, then statuses, then return shape — a logical order with no filler. The return-value sentence is long and dashes-heavy but every clause carries information.

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?

No output schema exists, and the description compensates by naming the report structure, report_url, and markdown_summary so the agent knows what it receives. A single-param poll tool has few remaining gaps beyond poll timing.

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% and the schema already says job_id comes from run_aeo_report; the description adds no new parameter detail beyond reiterating the job identity implicitly. Baseline 3 applies.

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?

States a specific verb+resource+scope: 'Poll a previously submitted AEO report job once'. This clearly distinguishes it from the sibling run_aeo_report (which submits the job) without requiring the schema to be opened.

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 ... once' plus the status taxonomy tells the agent exactly when to call again ('keep polling') versus stop ('terminal'). It doesn't name an alternative or state a polling interval/backoff, which keeps it from a 5.

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

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

Annotations cover the safety profile (non-readonly, open-world, non-destructive), and the description adds meaningful operational context: the run can take ~10 minutes, the report is delivered by email, and a shareable report URL is returned. It does not mention the idempotency-key requirement for agency-path retries, which is a notable omission for a job-creating call.

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?

Three tight, front-loaded sentences that lead with what the report is and then the operational constraints. The trailing 'Never fill the company field' is slightly confusing since no company parameter exists in this schema, costing a bit of signal.

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 an 11-parameter job-creating tool with no output schema, the description covers the key unknowns: latency, delivery mechanism, the returned URL, and the polling alternative. It leaves the agency-key/idempotency behavior and the exact job-payload response shape to be inferred.

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 every parameter is already documented in the schema; the description mostly restates the email requirement and the wait_seconds tradeoff without adding format or constraint detail beyond it.

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?

States a concrete verb+resource ('Run the free AI-visibility report for a website') and enumerates what the report covers (ChatGPT, Perplexity, Gemini, Claude, competitor gaps, fixes), which lets an agent tell it apart from get_aeo_report_status immediately.

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?

Explicitly gives the two execution paths: set wait_seconds up to 50 to wait inline, or poll later with get_aeo_report_status. It also states the prerequisite (a real email is required) and an exclusion ('Never fill the company field'), so the when/how decision is fully specified.

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