SEC filings

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

Beyond the annotations (readOnly, idempotent, openWorld, non-destructive), the description discloses the billing model (0.04 credit per returned filing/figure, failures and missing data not charged) and the absence of earnings-date data or any forecast/recommendation. Those are genuinely behavioral facts an agent cannot get from the schema, though excerpt length and truncation behavior remain unspecified.

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 core capability is front-loaded in the first sentence and the operational details follow in order of importance. Some sentences are filler or ambiguous boilerplate, notably 'Reads a filed SEC fact for one US ticker,' which duplicates earlier content, and the trailing signup URL key that reads like marketing rather than tool guidance.

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?

With no output schema, the description carries the burden of describing the return, and it does so: a filing document plus a short plain-text excerpt. Cost, failure handling, and scope limits are covered; remaining gaps are the excerpt's size/truncation and the valid set of form values, which matter for a free-string parameter.

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%, so both parameters are already documented, and the description largely restates them. It does add the effect of omitting 'form' (returns the latest among three form types) and an example value, but nothing about allowed form values beyond the free-form string or what happens if an unsupported form is requested.

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 first sentence names a specific verb (return) and resource (latest 10-K/10-Q/8-K for a US ticker) and states the payload includes a plain-text excerpt of the primary document. It does not explicitly distinguish itself from the sibling reported_figure, and the later sentence 'Reads a filed SEC fact for one US ticker' partially blurs the line between filings and figures rather than sharpening it.

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?

It gives one concrete usage hint: set 'form' to request a single type, e.g. 10-K. It also rules out a common wrong expectation ('The next earnings date is not in EDGAR and is not guessed'), which is a useful when-not. However, there is no guidance on when to use this tool versus the sibling reported_figure, which is the main selection decision an agent faces here.

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

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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so the safety profile is covered. The description adds genuinely non-obvious behavior: a 0.04 credit charge on a returned figure and no charge on missing ticker, missing filing, or failed fetch. It stops short of describing the return shape, but the billing semantics are the highest-value addition here.

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 core sentence is well front-loaded, but the forecast disclaimer is repeated twice in slightly different wording and the signup URL sits in the operational body rather than a separate note. Several sentences could be merged without losing information.

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 two-parameter lookup this covers the essentials, but with no output schema the description never says what comes back beyond 'a number' - no indication of units, currency, fiscal year end, or the accession/form reference. That is a real gap an agent would want closed before relying on the value.

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% with an enum on measure, so both parameters are already fully documented. The description adds only the implicit constraint that the figure is the latest full-year value, without clarifying period selection, currency, or units. Baseline 3 is appropriate.

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?

"Return the latest full-year revenue or net income from a 10-K in SEC company facts" gives a specific verb and resource plus the exact data source. It does not explicitly contrast with the sibling latest_filing, so an agent must infer that latest_filing returns documents while this returns a single figure.

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?

It states the domain (one US ticker, filed SEC facts) and constrains measure to revenue or net_income, which implies when it applies. It never says when to prefer latest_filing or what to do when a company reports the measure under a non-standard tag, leaving the sibling choice to inference.

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