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

Goes well beyond the readOnlyHint annotation: explains that counts is always the complete tally while limit bounds each row list, that split-like deltas are withheld into split_suspect with as-filed counts, that share classes are never summed/netted, and that CUSIP-resolution makes figures approximations. It also names the source (SEC EDGAR 13F-HR) and cost profile.

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 purpose, then return shape, then behavioral caveats and source. Dense but every clause carries information. Slightly packed with parentheticals, but no wasted sentences.

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?

No output schema exists, so the description carries the return-burden and does so: it enumerates the response fields and explains the tricky ones (counts, split_suspect). Edge cases, data provenance, and limitations are all covered, leaving nothing an agent needs to call it correctly.

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 100%, so the baseline is 3, but the description adds real meaning: it clarifies that limit bounds EACH row list while counts remain the complete tally, which is the key semantic distinction an agent needs. It adds a bit beyond the schema's own description of limit.

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 and resource: 'Quarter-over-quarter institutional accumulation/distribution for one ticker,' with the classification scheme (new/increased/decreased/exited) spelled out. It explicitly distinguishes itself from the sibling get_institutional_holders by calling that tool a 'snapshot' and positioning this as the flow read.

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?

Frames the use case as the 'who is moving on X?' flow read and names the complementary tool (get_institutional_holders) and its distinction (snapshot). It does not give explicit when-not-to-use guidance, but the context and alternative are clearly stated.

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