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

Annotations already establish readOnly/idempotent/non-destructive, and the description adds genuinely non-obvious behavior: rows whose wordings were all dismissed are omitted, locked pages are customer-marked off-limits and must never be changed, unquoted contradictions are excluded and counted elsewhere, and cursor/reset rules for pagination. This is real context beyond the structured hints, though it doesn't touch permissions or rate limits.

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?

Purpose is front-loaded, which is good, but the middle is a dense run-on enumerating every returned row field (site_page, wording_count, group_ids, platforms, last seen, dismissed_wording_count, example wording, open action, other_page) that is hard to parse and mixes return-shape documentation with usage guidance. Several clauses earn their place (dismissed rows, empty-list semantics, cursor), but the whole is longer than needed.

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 usefully documents the returned row structure, the dismissed/locked/unquoted exclusions, and pagination termination ('null on the last page'), which is close to complete for a complex listing tool. The undocumented limit parameter and the enum values for window are the remaining holes.

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 0% across five parameters, so the description must carry the load. It explains cursor ('pass next_cursor verbatim') and implies window/filters via the devtune_get_accuracy parallel, but it never clarifies the 30/90 window enum or the meaning of limit, intent, and platform, leaving real gaps against a 0%-documented schema.

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 opens with a specific verb and resource ('List Accuracy's contradictions once per site sentence they conflict with') and immediately scopes it to the same window/filters as devtune_get_accuracy, which distinguishes it from the sibling devtune_get_accuracy_contradiction and the parent accuracy tool. 'What the tab's contradictions table shows' anchors the agent to a concrete artifact.

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 clear context for use: same window/filters as devtune_get_accuracy, pass next_cursor verbatim as cursor and leave other arguments unchanged, and it explains that an empty list means no contradiction names a site sentence rather than nothing being contradicted — redirecting the agent to unquoted_contradictions in devtune_get_accuracy. It stops short of explicitly naming when to prefer this over devtune_get_accuracy_contradiction or the claim-level siblings, so it is strong but not fully explicit about alternatives.

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