submit_agent_pitchPersist a validated pitch for AFA human review. Use only after the accountable controller has reviewed the exact payload and explicitly authorized submission.
| Name | Required | Description | Default |
|---|---|---|---|
| pitch | Yes | ||
| idempotency_key | Yes | A stable unique key reused for retries of this exact submission. | |
| controller_authorized | Yes | True only after the controller explicitly authorizes this exact submission. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate non-read-only, open-world, and destructive behavior. The description adds context about human review and the requirement for explicit authorization, which are useful behavioral traits beyond annotations. It does not fully elaborate on side effects, but the annotation coverage lowers the burden, and the added context is meaningful.
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 long: the first states the core purpose, and the second states the usage prerequisite. It is front-loaded, concise, and every word contributes value without redundancy.
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 purpose and usage guidelines but lacks explicit mention of response behavior or idempotency details. Given the tool's complexity (nested schema, no output schema), the absence of return-value or post-submission behavior information is a noticeable gap. However, the schema and annotations provide some context, making it adequate but not fully 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?
The schema provides a detailed structure for the pitch object with nested properties, and the top-level fields have some descriptions for controller_authorized and idempotency_key. The description does not add parameter details but implies the payload must be validated. With schema coverage at 67% and a comprehensive schema, the description's parameter contribution is minimal, but the schema itself carries the semantics.
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 persists a validated pitch for AFA human review, using the specific verb 'persist' and the resource 'validated pitch'. It distinguishes from siblings like validate_agent_pitch, which likely only validates, and emphasizes the authorization prerequisite, making the purpose precise and non-tautological.
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 explicitly states 'Use only after the accountable controller has reviewed the exact payload and explicitly authorized submission,' providing a clear precondition. It does not explicitly name alternative tools, but the sibling names and the conditional context imply this is the final submission step after validation, which is sufficiently clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Tools are mostly distinct: pitch lifecycle (check, validate, submit, report) vs. capital/resources discovery (get, search, open). Slight overlap between get_live_capital_opportunity, get_open_capital_opportunities, and search_live_capital_opportunities, but descriptions clarify difference between get (specific record) vs search (general) vs open (current grants). Could be clearer with verbs like 'get_opportunity_by_id'.
Follows consistent verb_noun pattern: check_, get_, search_, validate_, submit_, report_ with clear objects (pitch, capital_opportunity, resource, milestone). Minor inconsistency: 'get_open_capital_opportunities' (adjective) vs 'search_live_capital_opportunities' (adjective) but they are distinguishable. Mixed use of 'opportunity' vs 'opportunities' is fine.
9 tools is well within the ideal 3-15 range. Each tool has a distinct role in the two core domains (pitch management and resource discovery). No redundancy or bloat; count is appropriate for the scope.
Covers pitch lifecycle (existence, validation, submission, milestone reporting) and resource discovery (search, get, live opportunities). Missing obvious update/delete operations for pitches or milestones; no 'delete_pitch' or 'update_pitch'. Also lacks a tool to list all venture resources without search (but search likely covers). Minor gaps but core workflows are covered.