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

Goes well past the readOnly/idempotent annotations by disclosing per-action credit costs, the fact that out-of-plan companies return 403 and are still charged, and the default exclusion of rows failing a consistency check with the omitted count reported. These are decision-relevant behaviors (cost, failure, data filtering) that no structured field carries.

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 one-sentence model of the resource, then a bullet per action with cost, then the plan/403 caveat last. Dense but every line carries information an agent needs to choose an action, and there is no 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?

For a 28-parameter, 7-action tool with no output schema, the description covers what each action returns, how ids flow between actions, cost, and pagination behavior. Remaining gaps are error handling beyond the 403 case and any differentiation from sibling data tools, which is a minor shortfall rather than a blocking one.

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 description coverage is 100% and the schema itself annotates each parameter with its applicable actions, so the description correctly stays out of per-parameter restatement. It adds a little beyond the schema — the A/D direction meaning and the id handoff between stats and get — but most parameter meaning is already schema-side, so the baseline of 3 applies.

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?

Names a specific resource (insider trades reported on SEC Form 4/5) plus the exact data shape returned (filing-nested transactions with insiders, footnotes and filing links), then enumerates all seven actions so the agent knows the tool is a multi-action surface rather than a single lookup. It also disambiguates the direction field (acquired_disposed_code A/D), which an agent could otherwise misread.

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 routes between actions: stats outputs ids that get consumes, insiders outputs the insider_cik that list/stats take, types is the lookup for transaction_code, search is plan-gated. That is real when-to-use guidance. It does not, however, say when to prefer this tool over siblings like akkru_filings or akkru_institutional_holdings, so the sibling boundary is left to inference.

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