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

Goes well past the annotations: it discloses the 3-year lookback window, that every item is linked to its source filing, that 424B5s are quoted with extracting sentence, the interpretive caveat ('Signs, not a verdict'), plus auth mechanics (Bearer agent key) and the cost model (5¢/call, 3 free premium calls/day). That is material context an agent needs that readOnlyHint/openWorldHint cannot convey.

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 the framing question and densely packed, but the middle sentence is a single sprawling list of ~10 items joined by commas and 'and', which slows parsing. Little is wasted, yet a bulleted or segmented structure would read faster for an agent scanning for scope.

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?

There is no output schema, and the description compensates by describing the returned items, their filing links, and even the quote-with-source treatment for 424B5s. Combined with annotations covering the read-only/open-world profile and 100% schema coverage on the one parameter, an agent has everything needed 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?

The tool takes a single parameter and the schema already documents it at 100% coverage ('Ticker, company name or SEC CIK'). The description adds no identifier format guidance, resolution behavior, or failure mode for ambiguous names, so it sits at the baseline rather than adding value.

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?

Opens with a specific question the tool answers ('Is a company issuing, or set up to issue, new shares?') and then enumerates the exact SEC-filing evidence returned: shares outstanding vs. 1 and 3 years ago, S-3/S-3ASR/F-3 shelves, 424B supplements, 8-K item 3.02, warrants, convertibles, authorized-share headroom. This is unmistakably a share-dilution research tool and cannot be confused with siblings like insider_trades or company_financials.

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?

Explicitly names trigger phrasings: 'does X have dilution', 'is X diluting', 'does X have an ATM / shelf'. It also pre-empts a common misuse by warning that a shelf is a signal, not proof of sales. It stops short of naming a sibling alternative to use instead (e.g. filing_search for raw filing lists), so the alternatives dimension is absent.

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