Figurewell

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

Annotations already declare read-only, idempotent, non-destructive and open-world, so the safety profile is covered. The description adds real behavioral value the annotations do not: newest-accepted-first ordering, the 40-filing cap, values as first reported rather than restated, and the inclusion of EDGAR acceptance time and filing link. It omits pagination behavior (offset) and any rate/limit caveats.

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?

Two sentences, no filler, with the resource and ordering constraint front-loaded before the as_of clarification. Dense but every clause carries information; slightly over-packed into one long opening sentence rather than being maximally scannable.

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 read-only query tool with a fully documented 8-parameter schema, strong annotations, and no output schema, the description covers what an agent needs: the filing scope, the first-reported semantics, the point-in-time meaning of as_of, and the ordering. Nothing about calling it correctly is 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 description coverage is 100%, so every parameter including as_of, limit, offset, form, fields and amendments is already documented in the schema. The description restates the as_of constraint and the 40-filing cap but adds no syntax, format, or default detail beyond what the schema provides. Baseline 3 is correct when the schema does the heavy lifting.

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 (10-K/10-Q/20-F/40-F filings with revenue, profit, EPS, cash, debt, cash flow, margins) and a specific behavioral twist (metrics 'as each filing first reported them', point-in-time via as_of). An agent knows exactly what it returns. It does not, however, contrast itself against the siblings metric_history or snapshot_as_of, which is the only thing keeping it from a 5.

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?

Usage is implied by the phrase 'as_of = only filings accepted by then', which tells the agent the point-in-time semantics, but there is no explicit statement of when to choose this over metric_history or snapshot_as_of, and no stated exclusions or prerequisites. Adequate but leaves the routing decision to inference.

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, so safety is covered; the description goes further by disclosing return semantics — per-period granularity, newest-first ordering, both an as-reported and an as-of value, and a restatement flag. That restatement behavior is a non-obvious trait the agent would otherwise not know. It omits pagination behavior and any limits on history depth.

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?

A single dense sentence with no filler, and the ordering constraint is front-loaded. The parenthetical '(and when)' is slightly cryptic and costs a beat of clarity, but nothing is wasted.

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 does so reasonably: it explains the row grain, ordering, the two value columns, and the restatement flag. It does not address units, null handling, or what happens when history is shorter than limit.

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 the schema already documents as_of, limit, metric, period, and ticker. The description reinforces the newest-first ordering and the as-of cutoff but adds no syntax, format, or edge-case detail beyond what the schema states. Baseline 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?

The description names the resource precisely — a single metric's history, one row per period, ordered newest first — and enumerates the payload fields (as-reported value, as-of value, restated flag). It does not name or contrast with the siblings financials_as_of or snapshot_as_of, so an agent must infer the distinction from the point-in-time wording.

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?

There is no explicit when-to-use guidance, no stated prerequisites, and no mention of when to prefer this over financials_as_of or snapshot_as_of. The as_of clause hints at point-in-time querying but never tells the agent when that mode is appropriate.

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 readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is covered. The description adds one genuinely useful behavioral nuance the annotations cannot carry: 'as first reported' signals that values are original filings, not restated figures. However it says nothing about the shape or size of the result, what 'key metrics' includes, or what happens when a ticker has no accepted filing by as_of.

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?

A single sentence with zero filler; every clause (ticker cap, point-in-time acceptance rule, first-reported semantics) earns its place. The scoping constraint is front-loaded and the sentence reads cleanly without repetition of schema fields.

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, so the description carries the burden of explaining what comes back, and it does not: 'key metrics' is undefined, the response structure is unknown, and edge cases (no filing by as_of, invalid ticker, more than 10 tickers) are unaddressed. Combined with the missing sibling routing, the definition is under-specified for an agent to invoke confidently beyond the happy path.

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 tickers, cik fallback, the form enum, and the as_of timezone convention are all documented in the schema itself. The description only echoes the 'up to 10 tickers' cap rather than adding semantics (e.g., default metric set, behavior for unknown tickers), so the baseline 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?

The description states a specific resource and scope: the newest filing EDGAR had accepted by a given instant, plus key metrics as first reported, for up to 10 tickers. An agent can form a clear mental model of the operation. It falls short of 5 because it never names or contrasts the siblings (financials_as_of, metric_history), so differentiation from the point-in-time financials tool must be inferred.

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?

There is no explicit when-to-use statement, no exclusions, and no named alternative. The closest thing to guidance is the implicit contrast between a point-in-time snapshot and a history tool (metric_history), but the agent has to supply that inference itself. For a tool sitting alongside financials_as_of, the absence of routing guidance is a real gap.

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