Fill in or correct a stored project. Facts and pack are merged into what is there, so you can add one field at a time as the maker answers.
| Name | Required | Description | Default |
|---|---|---|---|
| url | No | ||
| name | No | ||
| pack | No | ||
| facts | No | ||
| pitch | No | ||
| projectId | No | Omit it when the account has one project, which is the free tier. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It explicitly discloses the merge semantics ('Facts and pack are merged into what is there') and the incremental nature, which is critical for an agent to know it won't overwrite unmentioned fields. It does not cover error cases or idempotency, but the core behavior is transparent.
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 a single, concise sentence that front-loads the purpose and key behavior. It avoids verbosity and is easily scanned. However, given the tool's complexity, it is almost too terse—it omits context that might be expected at this level, though it remains structurally efficient.
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 tool has complex nested objects and many optional fields, yet the description ignores how to select the project (projectId), what happens if no projectId is given, and how pack relates to facts. With zero annotations and low schema coverage, an agent lacks critical context to call this tool correctly without additional probing.
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 17%, yet the top-level description adds no parameter-level explanation. It does not clarify that 'projectId' is optional or how 'pack' and 'facts' relate. The schema itself covers some nested fields, but the description fails to compensate for the low coverage, leaving many parameters underspecified.
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 a specific verb ('Fill in or correct') and resource ('a stored project'), which unambiguously distinguishes it from create_project. It also communicates the incremental merge behavior, leaving no doubt that this tool patches existing data rather than creating new records.
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 hints at a usage pattern ('as the maker answers') but gives no explicit when-to-use guidance, no alternatives, and no exclusions. It does not mention that create_project should be used for new projects or that qualify_project fills gaps, so an agent must infer when to choose this tool.
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 target a distinct resource/action: projects vs platforms vs submissions vs account, and pairings like search_platforms/get_platform and qualify_project/plan_submissions are separated by clear scope. The only mild ambiguity is get_platform with brief=true vs submission_playbook, since both can return the same form brief, but one is generic and the other is project-specific.
Tool names overwhelmingly follow verb_noun snake_case (create_project, list_submissions, qualify_project, record_submission). The exceptions are whoami, a common idiom rather than verb_noun, and submission_playbook, a noun phrase instead of something like get_submission_playbook, so the pattern is strong but not perfect.
11 tools is comfortably within the well-scoped range for a domain covering projects, platforms, submissions, planning, and account identity. Each tool maps to a recognizable workflow step and none feel redundant.
The set covers the core lifecycle: create/read/update projects, search/read platforms, qualify and plan, list/record submissions, and identify the account. It lacks delete_project and a way to retrieve an existing plan or edit a submission record, but those are workable gaps rather than blockers.
