voicebrief

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

Annotations already declare readOnlyHint=true and destructiveHint=false, covering the safety profile. The description adds valuable behavioral context: it grounds results in the most recent 10-K via EDGAR XBRL, emphasizes 'not a guess' (implying accuracy), and specifies the output as a single natural-language sentence. This goes beyond the structured fields.

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 description is two sentences, front-loaded with the core purpose. The first sentence states the function and constraints; the second gives usage examples and the metric list. It is concise and every clause adds information, though it could be slightly tighter.

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, single-metric tool with no output schema, the description covers data source, output format, allowed metrics, and usage context. It does not mention edge cases like missing metrics or error handling, but these are not critical for correct invocation given the annotations.

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 both parameters have descriptive text. The description's restatement of allowed metrics mirrors the enum, and the company example adds no new meaning beyond the schema. Per the rubric, baseline 3 is appropriate when the schema already documents parameters fully.

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 clearly states the tool's action: 'Answer one financial metric for a US public company' and specifies the grounding in SEC 10-K filing data. It enumerates the allowed metrics and differentiates from the sibling get_stock_snapshot by emphasizing 'one metric' versus a snapshot, which implies a scope distinction.

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?

The description gives explicit usage context: 'Use for a specific spoken question like...' and provides examples. However, it does not explicitly state when NOT to use it or name the alternative tool (get_stock_snapshot) as a better choice for multiple metrics. The guidance is clear but lacks explicit exclusions.

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=true and openWorldHint=true, covering the safety profile. The description adds valuable context: the snapshot is 'grounded in its most recent SEC 10-K filing' and is a 'short spoken financial snapshot', which informs the agent about data source and output format beyond what annotations provide.

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 description is two sentences with zero redundancy. The first sentence fronts the purpose and output specifics; the second gives usage guidance. Every phrase earns its place, and the overall length is appropriate for the tool's simplicity.

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 single-parameter read-only tool with no output schema, the description is nearly complete. It covers the data source, output type, and usage scenario. It does not mention edge cases (e.g., missing 10-K, non-US companies), but these are minor and not critical for correct calling.

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%, with the 'company' parameter fully described as a name or ticker with examples. The tool description adds no additional parameter-level detail, so the schema already carries the burden. This matches the baseline for high schema coverage.

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 verb ('give'), a resource ('US public company'), and lists the exact metrics returned (revenue, EPS, market cap, book value per share), plus the data source (most recent SEC 10-K filing). It also explicitly differentiates from the sibling get_stock_metric by saying 'rather than one specific figure', making its scope unmistakable.

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?

The description provides clear when-to-use guidance: 'Use for a broad spoken question like "tell me about Apple's financials" rather than one specific figure.' This implies the alternative (get_stock_metric) but does not name it explicitly. It gives a strong negative condition and usage context, but falls short of naming the sibling tool directly.

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