projects_create_riskLog a new project risk. Category: Technical|Schedule|Financial|Contract|Communication|Other. Status: Open|In Progress|Closed. responsible_owner must be an employees.id in your workspace (use hr_get_employees to look it up).
| Name | Required | Description | Default |
|---|---|---|---|
| title | Yes | ||
| impact | No | ||
| status | No | ||
| category | No | ||
| project_id | Yes | ||
| description | No | ||
| probability | No | ||
| responsible_owner | No | employees.id - not an auth user id. | |
| mitigation_actions | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already signal the mutation is read-write and non-destructive; the description adds useful constraints such as allowed category/status values and the employees.id requirement within the workspace. It does not disclose side effects, duplicate handling, or other behavioral caveats, but the annotation safety profile lowers the burden.
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?
Three short sentences carry only high-value information: the action, the exact allowed values for two constrained fields, and the lookup requirement for the foreign key. Nothing is padded or repeated.
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 is adequate for a basic call because required fields are apparent from the schema and the tool name, and the owner constraint is covered. It is not fully complete for nine parameters: it never explains the meaning of impact/probability, whether category/status are optional, or how project_id should be resolved to an existing project.
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 only 11%, and the description compensates for a few parameters by listing valid categories, statuses, and the responsible_owner lookup rule. Required project_id/title and the impact/probability scale remain underspecified, so the compensation is only partial.
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 'Log a new project risk,' which names a concrete action, the resource, and the 'new' state that distinguishes creation from the update/delete/get siblings. There is no ambiguity about what this tool does.
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 creation context is clear and the description adds a specific prerequisite: responsible_owner must come from hr_get_employees. It does not explicitly say 'use projects_update_risk for existing risks,' so it falls just short of fully explicit routing between 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.
Most tools follow a clear resource+action pattern and the descriptions are unusually precise about boundaries. A few near-overlaps remain: projects_get_finance vs projects_get_financials, and notes_create vs crm_log_activity on a deal are both plausible for recording a note on a deal.
The domain_prefix_action convention is consistent across nearly all tools, e.g. crm_create_lead, projects_update_risk, timelog_approve_time. Deviations include standalone list_trash, meta tools like whoami/tool_search/tool_invoke, and the confusing projects_get_finance/projects_get_financials pair.
With 105 tools, this far exceeds the 50+ threshold defined as an extreme mismatch. Even for a full ERP/CRM suite, the fine-grained split—39 project tools alone—creates a massive tool-selection surface that is hard for an agent to navigate reliably.
The surface covers CRM, projects, tasks, time/expenses, HR, notes, notifications, contracts, and reporting with create/read/update/delete for most primary entities. Minor gaps exist: crm_log_activity has no read-back path, contracts lack delete/restore, and proposals are intentionally read-only, but agents can work around these.