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

The description directly contradicts the annotation openWorldHint=false. The description states that 'a miss is a dataset-coverage result, not proof that a fund does not exist', which implies an open-world interpretation, while the annotation marks the tool as closed-world. This is a significant inconsistency that could mislead an agent about how to interpret missing results.

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?

The description is three sentences, each contributing meaningful information. The purpose is front-loaded, and the coverage caveat is placed at the end. It is efficient without being terse, though the third sentence is slightly lengthy. Overall, it is well-structured and concise.

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?

The description covers the return fields (ticker, registration type, latest report date, assets, holding counts) despite the lack of an output schema, which is helpful for an agent. It also notes the ranking behavior and the usage handoff. However, it does not address potential errors, pagination, or limits beyond maxResults, leaving minor gaps. Given the tool's moderate complexity and absent output schema, the coverage is fairly complete.

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?

The input schema covers both parameters with descriptions (100% coverage), so the baseline of 3 applies. The description adds a minor detail about matching behavior ('Exact stored tickers outrank verified share-class aliases') but does not add new parameter formats or examples beyond what the schema already specifies. No extra semantic value beyond the schema.

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?

The description clearly specifies the verb 'Search' and the resource 'tracked SEC Form NPORT-P fund directory', and differentiates itself from siblings like SearchInstitutions and SearchDocuments by naming the specific domain (funds/ETFs) and the source (NPORT-P filings). It also states what is returned (canonical profile per series with ticker, registration type, etc.), so an agent knows exactly what the tool does.

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?

The description explicitly instructs to 'Use the profile ID with GetFundProfile', which tells the agent when to hand off to a sibling. It also provides context on dataset coverage ('directory covers NPORT-P filers; a miss is a dataset-coverage result'), which helps the agent interpret results. It does not explicitly list when not to use it, but the pointer to GetFundProfile and the coverage note are strong usage guidance.

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