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

Annotations already cover read-only/idempotent safety, but the description goes far beyond: it explains plan-based gating ('fields the plan doesn't include come back null and are named in that item's locked list'), defines lockedCount and estimates, instructs 'never estimate it yourself', notes nothing is shown to the user yet, and states it needs no Replo account. This is exactly the extra 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?

Long but densely front-loaded: purpose first, then filters, then plan gating, then the show workflow and the auth note. Nearly every sentence carries operational weight, though the two-part emphasis on locked fields/plan messaging is slightly repetitive.

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 tool with no output schema, the description covers the non-obvious return behavior (locked fields, lockedCount, resultId for sightglass_show) and the auth precondition. It does not describe the general shape of a returned page record or restate pagination, leaving a small gap.

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?

With 70% schema coverage the baseline is a 3, but the description adds real meaning: it enumerates the semantic values and clarifies that `search` is semantic over title and description (not documented in the schema), and gives concrete technology examples (Shopify, Klaviyo). It still leaves `sort` and `activeAdsCountGte` unexplained, so not a 5.

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+resource ('Find destination pages ads drive to') and immediately disambiguates the jargon by equating it to 'landing pages'. It is clearly distinguishable from siblings like sightglass_get_site_page (single page) and sightglass_find_ads/find_technologies (different resources).

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 explicit pipeline guidance: this tool returns data only, then call sightglass_show once with resultId to render cards, and it can be called before the user signs in. It does not, however, contrast itself against the other find_* siblings (e.g. when to use find_technologies over this), which keeps it short of a 5.

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