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

The description goes well beyond the annotations (which only cover read-only/idempotent safety) by disclosing sampling limits (28 days, at most 50 queries and 50 pages), the fact that coverage is partial and tied to this property rather than market volume, that positions are impression-weighted averages rather than fixed SERP ranks, and that credentials and raw provider responses are never returned. It also flags collection failure as something to verify before acting. This is exactly the kind of behavioral context annotations cannot carry.

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 opening sentence is well front-loaded with the core capability, but the text is long and repeats itself: the 'not market search volumes' caveat appears twice, and the positions 4-20 / up-to-20-queries limits are restated in separate sentences. Repetition of the same caveats crowds out room for other 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?

With no output schema, the description must explain what comes back, and it does: keywords, opportunities, the terms array, daily history and comparison windows, plus the statistical caveats on how positions and impressions are computed. That is close to sufficient for a read-only, single-parameter tool; only the workflow ordering relative to connect/sync siblings remains unstated.

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 single 'id' parameter is already documented in the schema as coming from list_sites or add_site, so the baseline is 3. The description instead spends effort describing a 'terms array' with daily history and 7-day comparisons that does not exist in the input schema, which adds confusion rather than 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 states a specific verb and resource: read own-site keyword data (keywords, opportunities, tracked queries, daily history) for a given site ID. It also draws a clear boundary against market search volumes, which helps separate it from visibility-oriented siblings. However, it never names or contrasts with competing siblings such as sync_search_console, track_search_queries or ai_search_visibility, so differentiation is only partial.

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 gives task-level guidance: 'Check dates, partial coverage and collection failure before proposing edits' and 'Use queries for keyword research and opportunities for average positions 4-20.' That is useful workflow direction, but it is guidance on reading the output rather than on when to call this tool instead of a sibling. No explicit alternatives or prerequisites (e.g., connect_search_console first) are named, so usage is implied rather than stated.

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