projects_add_documentRegister a project document reference. Provide file_path (already uploaded to storage) and file_name.
| Name | Required | Description | Default |
|---|---|---|---|
| file_name | Yes | ||
| file_path | Yes | ||
| file_size | No | ||
| mime_type | No | ||
| project_id | Yes | ||
| document_type_id | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate this is not read-only and not destructive; the description adds meaningful behavioral context by clarifying it only registers a reference and does not upload the file itself. This helps the agent avoid assuming storage behavior. It stops short of describing the response, but the core side-effect is well communicated.
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 sentences with no filler: the purpose comes first, then the key prerequisite and required fields. Every sentence earns its place.
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 the essential invocation path—required fields and the storage prerequisite—so an agent could likely call the tool correctly. However, there is no output schema, optional parameter guidance is missing, and the description does not indicate what happens after registration, such as whether an ID or confirmation is returned.
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%, so the description carries full responsibility for explaining parameters. It only clarifies file_path and file_name, leaving project_id, document_type_id, file_size, and mime_type unexplained. With six parameters, this is a significant gap.
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 uses a specific verb ('Register') and resource ('project document reference'), and the phrase 'already uploaded to storage' distinguishes this from an actual file-upload operation. This clearly separates it from sibling tools like projects_delete_document or projects_get.
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 implies the tool should be used only after the file has been uploaded to storage by saying 'file_path (already uploaded to storage)'. However, it does not explicitly state when to use this tool versus alternatives like projects_delete_document, nor does it mention conditions around optional parameters like document_type_id.
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.