Fundz Agent API

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

Annotations already cover read-only and idempotent behavior. The description adds cost information ('Costs 1 unit') and mentions ranking/evidence, which are behavioral details. No contradictions with annotations.

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 concise sentences with no fluff. Well-structured and directly addresses the tool's purpose and key usage.

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?

Provides enough context to understand the tool's function and expected output (ranked evidence). No output schema is required. Minor gap on parameter details, but overall complete.

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?

Only `min_signals` is explained in the description, and `limit` and `states` have schema descriptions. The remaining parameters (cursor, industries, lookback_days, min/max_employees) are unexplained, resulting in low coverage. The description does not compensate for these gaps.

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?

Clearly states the tool finds companies matching an ICP with recent funding or SEC 8-K events, ranked with evidence. The phrase 'build a list from scratch' differentiates it from sibling tools like watchlist_diff.

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?

Provides a direct use case: 'Use this to build a list from scratch.' While it does not explicitly contrast with siblings, the phrase implies initial list creation, offering sufficient guidance.

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 mark the tool as read-only, open-world, idempotent, and non-destructive. The description adds valuable behavioral context beyond annotations, including experimental status, the meaning and limitations of lift and base_rate, forward-cohort resolution dates, a 1-unit cost, and an end-user restriction.

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 compact and front-loaded with the core purpose, followed by necessary caveats and cost information. Every sentence adds relevant operational or interpretive value, with no redundant or filler content.

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?

The description covers output-related cautionary context and cost but omits essential input parameter semantics and does not describe the output structure beyond lift and base_rate. Given the lack of an output schema and parameter descriptions, it is not sufficiently complete for confident invocation.

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 input schema has two parameters—domain and org_id—with no descriptions, and the description makes no mention of either parameter. With 0% schema description coverage, the tool description fails to explain what these inputs mean or how they affect the forecast.

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 purpose: producing an experimental forecast of specific company actions (raise, be acquired, acquire, hire an executive) from FundzScore v3. It is concrete and distinct from sibling tools that focus on events, watchlist diffs, or causal explanations.

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 important usage cautions: treat lift as a ranking aid, base_rate is a population mean, cohorts resolve on specific dates, and do not present predictions to end users. However, it does not explicitly say when to choose this tool over the sibling tools or provide selection criteria.

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?

Beyond the readOnly/idempotent annotations, it discloses that costs accrue per company checked even if nothing is returned, and that request bodies are capped at 8 KB. It also explains cursor-based incremental behavior.

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 front-loaded with the main purpose and then adds cost and splitting guidance. It is slightly repetitive in explaining per-company pricing, but all sentences are relevant.

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 tells the agent what is returned (only companies with new evidence) and how to handle limits/cost. It could be more explicit about the response shape or the next_cursor returned, but it is sufficient for basic invocation.

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 since parameter is described as the next_cursor from a previous call and domains are implicitly described as company domains up to 400, with an 8 KB cap. However, the domains parameter lacks an explicit schema-level description and the optional behavior of since is not stated.

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 that the tool accepts a book of up to 400 company domains and a cursor and returns only companies with new evidence since that cursor. This is specific and distinct from the sibling tools by focusing on incremental polling.

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 explicitly says this is the tool to poll daily or weekly rather than re-fetching every company, and provides concrete guidance on splitting larger books across calls due to the 8 KB cap and per-company pricing. This gives an agent clear when-to-use and how-to-use context.

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, openWorldHint, idempotentHint, and destructiveHint, so the description doesn't need to restate those. It adds substantial behavioral context: the cost of 1 unit, the distinction between evidence and last_event, within_lookback flag, the meaning of resolved:false, and the resolution_confidence threshold. This goes well beyond what annotations provide and covers edge cases clearly.

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 detailed but well-organized, starting with purpose, then usage, then parameter behavior, then edge cases. Each sentence serves a purpose, and the density is justified by the tool's complexity. It is not overly verbose, though it could be slightly more compact without losing key details.

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?

Given there is no output schema, the description fully explains the expected output fields (evidence, last_event, within_lookback, resolved, resolution_confidence) and their interpretations. It covers the cost, the lookback window, and attribution confidence. It also handles the case where the company is not found. This is complete for an agent to invoke and interpret results 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?

Schema coverage is 67% (domain and lookback_days have descriptions; org_id does not). The description significantly enriches lookback_days by explaining its effect on evidence and that it does not limit last_event. It also reiterates the domain flexibility. However, org_id remains unexplained both in schema and description, leaving a small gap. Overall, the description adds meaningful semantics for the key parameter.

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 opens with a precise statement of what the tool does: 'Why to contact ONE company right now: dated funding and SEC 8-K evidence, each item linking to its source filing or announcement.' It uses a specific verb ('provide' or 'give'), names the resource (company), and clearly distinguishes itself from siblings by emphasizing 'ONE company' — implying the others handle multiple entities or different queries.

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 explicitly states when to use the tool: 'Use this when you have a company and need the reason and the proof.' It also explains different outcomes (empty evidence with last_event, resolved:false) and how to adjust lookback_days. However, it does not explicitly mention alternative sibling tools or conditions for not using this tool, though the 'ONE company' focus implicitly separates it from events_for_icp.

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