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

Beyond the readOnly/idempotent annotations, it discloses non-obvious behavior: restricted fields come back null and are enumerated in each item's `locked` list, `lockedCount` signals how many more results a higher plan would show, and the agent is instructed to tell the user the data is on a higher plan rather than estimate it. It also clarifies the tool is non-mutating with respect to the UI ("nothing is shown to the user yet") and works without an account.

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 definition and filtering capability, then the sequencing and plan-lock rules. It is dense but every clause carries operational information; the only mild redundancy is restating the show/return separation twice ("Returns data only" and "the show call does not search again").

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 10-parameter read tool with no output schema, it covers the important gaps: pagination contract is in the schema, the show handoff is explained, and plan-lock semantics are spelled out. What is missing is any indication of what fields a returned page item contains beyond `locked`/`lockedCount` and `resultId`, and how `sort` interacts with the semantic-match ordering.

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 70%, and the description adds real meaning on top: it explains the `search` tie-breaking algorithm (all-words title/description/URL match first, then semantic fill) and gives concrete technology examples (Shopify, Klaviyo). The pageTypes enumeration largely duplicates the schema's own CSV description, and sort values go unexplained.

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 a specific verb and resource ("Find destination pages ads drive to") and immediately maps the user's vocabulary ("what users call 'landing pages'") onto it. This cleanly separates it from sightglass_find_ads and sightglass_get_site_page, which deal with ads and single pages respectively.

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?

Gives concrete workflow guidance: call it before asking the user to sign in, then call sightglass_show once with the resultId to render cards, and explicitly states the show call does not search again. It also sets an expectation for plan-locked data. It never explicitly states when to prefer this over sightglass_find_ads or sightglass_search_companies, so it falls just short of full alternative routing.

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