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

Annotations already establish readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds genuine value beyond them: the data source (NPPA price filings) and the shape of the result (names, pack counts, counterfoil.in pages to cite), which matters since no output schema exists.

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?

Three tight sentences with zero filler. The entry-point guidance is front-loaded, then results, then the citation source — each sentence carries distinct information.

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 describes what comes back and where results come from. The one gap is the limit parameter and its hard cap of 10, which an agent must infer entirely from the schema.

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 50%: the query parameter is fully documented (brand/generic/company, three letters or more) in the schema itself, but the limit parameter has no description anywhere. The description adds only that matching is 'by name', which mildly clarifies query semantics but says nothing about the limit or its maximum of 10.

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?

Specific verb ('Find') plus three named resource types (brands, compositions/molecules, companies) scoped to NPPA's price filings. It also signals its role relative to siblings by saying 'Start here when you have a brand or generic name', which distinguishes it from get_brand/company_profile lookups.

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?

'Start here when you have a brand or generic name' gives a clear entry-point condition, and 'by name' rules out ID-based workflows. It stops short of explicitly naming alternatives like get_brand or compare_prices as the next step, so it's clear context but no explicit routing.

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