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

Annotations already declare read-only, idempotent and non-destructive, but the description adds material behavior annotations do not carry: data is stored and synced daily rather than a live crawl, workspace-wide calls cover only the 25 most recently synced sites for four issue types (with truncated: true indicating omissions) and up to 500 for ai-visibility/site-health, limit caps at 100 with no paging, total reports the match count, and calls cost 0 credits.

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 core purpose and dense with useful detail; every sentence contributes (type definitions, return fields, alternatives, scoping, limits, cost). It is delivered as a single long block, so a little more structural separation of scope and cost would improve scanability, but there is no filler.

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 three-parameter, no-output-schema list tool, the description covers everything an agent needs: what is returned (title, detail, evidence, affected pages, suggested_task, dashboard links, indexnow_urls), the workspace-wide truncation semantics, paging/limit behavior, and cost. Nothing material is left to inference.

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 already 100%, yet the description still adds meaning: it defines what each issue type actually detects (e.g., click-drop means at least 30% click loss over the last 4 weeks versus the prior 4; low-ctr is below half the usual CTR for the position), explains the consequence of omitting site_id, and clarifies limit's hard cap and no-paging behavior.

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 and resource ('List the problems RankParse has found on the user's websites') and anchors it to a concrete artifact (the Issues tab in the dashboard). It enumerates the six issue types, so an agent can tell exactly what this returns versus siblings like get_indexing_status or get_site_health.

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 routes to alternatives: get_indexing_status/get_gsc_url_inspection for one page's Google index details, recheck_ai_visibility after fixing a scan issue, and propose_indexnow_submit for the returned indexnow_urls. The scope rule for omitting site_id is spelled out in detail.

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