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

Annotations only declare write/openWorld/non-idempotent/non-destructive; the description adds the substantive behavior an agent cannot infer: a 24h cache refresh threshold, consumption of one daily Ad Spy lookup, free same-page-account-ad re-opens within a day, and the degraded path past the allowance (cached copy with meta.stale plus a meta.note the agent is told to relay). It also discloses plan and authorization prerequisites.

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?

Four sentences, front-loaded with the WRITE marker and the action, then cost, then failure mode, then prerequisites. Every clause carries information, though the final sentence packs quota, cache, plan, and auth into one dense run that could be split for scanability.

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 write tool with 8 params and no output schema, the definition covers everything an agent needs: where page_id comes from, what the returned payload looks like via the sonar_ad_spy_ads reference, what stale results look like, what the call costs, and what account/plan state 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 100%, with enums and ranges already documented for all 8 parameters, so the schema carries the load. The description adds only a pointer that filters match sonar_ad_spy_ads and a note that page_id derives from search_pages/scan — useful framing but no per-parameter semantics beyond structured data.

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?

Opens with 'WRITE tool' then a specific verb+resource: open a Facebook page from a recent search or scan and return its ads. It explicitly distinguishes itself from the linking flow ('without linking it to a competitor') and anchors the response shape to sonar_ad_spy_ads, so an agent can place it among sonar_ad_spy_link, sonar_ad_spy_ads, and sonar_ad_spy_refresh without opening schemas.

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?

States the entry condition clearly: the page_id must come from a recent search or scan (last 2 days), and the tool is the non-linking path. Cost conditions are spelled out (one daily lookup, same-day re-opens free, plan and scope requirements). The alternative tool is implied rather than named — it never says 'use sonar_ad_spy_link if you want competitor tracking' — so it falls just short of explicit when/when-not routing.

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