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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=true), so the description's real contribution is disclosing the detection logic and thresholds (positions 4–20, 'real impressions', CTR below positional expectation, comparison against the previous period). That is substantive behavioral context an agent cannot get from annotations or schema. It stops short of stating ordering/priority of the section output or rate/limit behaviour.

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 sentence that opens with the outcome ('quick SEO wins') before listing the four detectors, with zero filler. It is dense but the parallel list structure keeps it scannable; a bulleted form would read marginally faster.

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 10 optional parameters and no output schema, the description usefully pre-describes the result as four named sections, which is the main thing an agent needs to plan a response. The remaining gap is behavior on an empty call — default site selection, default date window, and whether all four sections are always returned — which matters because no parameter is required.

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 80%, so the baseline is 3; the schema already documents site, detail, country, dates and min_impressions. The description adds only indirect hints ('real impressions' echoes min_impressions, 'previous period' implies a comparison window), but never clarifies device, folder, or how date_range interacts with start_date/end_date.

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 analytical verb ('find ... wins') and enumerates the four exact opportunity classes it detects: striking-distance keywords with the 4–20 position band, under-performing snippets by CTR-vs-position, period-over-period query drops, and keyword cannibalisation. That enumeration makes it unambiguously distinct from the raw-reporting siblings (gsc_queries, gsc_performance, gsc_breakdown), which just return metrics.

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?

Usage is only implied: 'quick SEO wins' suggests diagnostic use, but the description never says when to pick this over gsc_queries or gsc_performance, nor when not to. There is no guidance on required input combination (site vs folder, date_range vs start/end), so an agent must infer selection from the schema alone.

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