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

Adds four behavioral facts absent from the annotations: a monthly research allowance is consumed only for newly tracked companies, results populate asynchronously, the call returns data only with nothing rendered to the user, and a separate sightglass_show call (which does not re-search) is required to surface results. These details reconcile the non-read-only, destructive-hinted annotations with the fact that the real cost is allowance consumption, not data loss.

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?

Five short sentences, front-loaded with the purpose, then cost, then async behavior, then the mandatory follow-up call. Every sentence carries a distinct, decision-relevant fact and none restates the name or title.

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?

Despite having no output schema, the description explains what comes back (a resultId and async-populated research data) and how to render it. Combined with the allowance and idempotency-of-cost notes, an agent has everything needed to call it and act on the result.

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 100% schema description coverage, both projectId and workspaceId are already documented in detail in the schema, including that the workspace's plan applies. The description only adds that the domain is the brand's website domain, which the schema example already conveys, so baseline 3 is appropriate.

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 compound verb ('find or add a company') plus the key action ('queue background research') scoped to a website domain, and enumerates what is researched (ads, landing pages, store details, technologies). This separates it clearly from read-only siblings like sightglass_get_company and sightglass_search_companies without needing to open either schema.

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 clearly establishes context: this is the entry point that dispatches research, and 'once you know the answer, call sightglass_show once with this call's resultId' defines the follow-up path. It does not explicitly state when to prefer it over sibling lookups such as sightglass_search_companies or sightglass_get_company, so the exclusion criteria are left implicit.

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