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

Annotations only declare readOnlyHint, so the description carries most of the burden and does so well: it discloses that split-suspect pairs are withheld with as-filed counts, that counts are complete while limit only bounds row lists, that share classes are never netted, and that CUSIP resolution makes figures approximate. These are exactly the behavioral traits an agent needs. Slight gap: no explicit note on auth or rate limiting, though a FREE public-domain SEC source implies none needed.

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?

Dense but front-loaded: the core purpose leads, followed by return shape, then limit semantics and caveats. It is long and parenthetical-heavy, but nearly every clause conveys a distinct behavioral fact rather than filler.

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 enumerates the return keys ({summary, ticker, quarters_analyzed, counts, new_positions, ...}) and explains the tricky fields (counts vs limit, split_suspect). For a read-only analytics tool this leaves nothing an agent needs missing.

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% and the schema already documents the limit default/cap, so baseline would be 3. The description adds real value beyond the schema by clarifying the crucial limit-vs-counts interaction (counts complete regardless), which prevents misinterpretation of the returned tallies.

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+scope: 'Quarter-over-quarter institutional accumulation/distribution for one ticker' with the classification buckets spelled out. It explicitly frames itself as the 'who is moving on X?' flow read and names the sibling it complements, so an agent can distinguish it from get_institutional_holders (snapshot) without opening 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?

Tells the agent when to reach for this vs the alternative: 'Complements get_institutional_holders (snapshot)' frames the delta-over-time use case against the point-in-time one. Combined with the explicit classification semantics (new/increased/decreased/exited), the selection criteria are clear.

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