Write back a conversion outcome for company_id -- the
label-flywheel substrate. Appends to outcome_labels scoped to the
caller's own customer.
Plane session only: `outcome_labels` is plane-owned (Phase 1 dropped its
one foreign key into the corpus) and this tool reads no corpus table.| Name | Required | Description | Default |
|---|---|---|---|
| outcome | Yes | ||
| req_key | No | ||
| company_id | Yes | ||
| observed_at | Yes | ||
| plane_api_key | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description provides good behavioral context: it appends to outcome_labels, is scoped to the caller's customer, requires a plane session, and reads no corpus table. Missing details on idempotency, errors, or side effects, but still informative.
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 short with two paragraphs, front-loading the purpose. The second paragraph adds relevant context about plane session restrictions. Somewhat cryptic references ('Phase 1 dropped its one foreign key') may distract, but overall concise.
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?
No output schema, and the description does not explain return values, error conditions, or idempotency. For a tool with 5 parameters and side effects, an agent lacks critical execution context.
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 0%, and the description only mentions company_id ('for company_id') without explaining outcome, observed_at, req_key, or plane_api_key. Little value added beyond the schema's structural info.
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 action ('Write back a conversion outcome'), the resource ('company_id'), and the effect ('Appends to outcome_labels'). It is specific and distinct from siblings, which are about hiring and changes.
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?
No explicit guidance on when to use this tool vs alternatives. The only hint is 'Plane session only', but no mention of conditions for not using it or comparison with sibling tools.
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.
Multiple tools have overlapping purposes (e.g., get_changes/get_open_reqs/get_role all retrieve job-related data with pagination; hiring_pulse and pre_action_brief share nearly identical descriptions; is_hiring and hiring_pulse both assess company hiring status). The long, verbose descriptions provide some subtle differentiators but the functional boundaries are unclear.
Naming patterns are highly inconsistent: some tools use 'get_' prefixes (get_changes, get_open_reqs, get_role), others are noun phrases (hiring_pulse, is_hiring, pre_action_brief) or verb phrases (register_webhook, watch_company, write_outcome). There is no uniform verb-object or resource-based convention, making it hard to predict functionality from names.
The server has 11 tools, which falls within the typical 3-15 range for a domain-specific API. However, several tools appear to serve redundant or narrowly-overlapping purposes (e.g., at least five tools deal with fetching job/company data), suggesting the count could be pruned without losing core functionality.
The tool set covers core operations like searching jobs, retrieving role details, checking hiring status, registering webhooks, and writing outcomes. However, there are notable gaps: no webhook management (e.g., list/unregister), no explicit company profile retrieval, and no update/delete operations. This makes the surface feel incomplete for a comprehensive hiring-signals API.