cap_table.deleteDelete the selected cap table and associated records after exact confirmation at the current version; existing shared access stops.
| Name | Required | Description | Default |
|---|---|---|---|
| project_id | Yes | ||
| cap_table_id | Yes | ||
| idempotency_key | Yes | ||
| expected_version | Yes | ||
| confirmation_token | No |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already convey destructiveness and non-read-only behavior. The description adds useful behavioral context beyond those flags: deletion cascades to 'associated records' and existing shared access stops, while the current-version confirmation requirement signals optimistic concurrency. This is a meaningful addition without contradicting the annotations.
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?
A single front-loaded sentence conveys the action, scope, condition, and side effect with no filler. It is concise while retaining all essential high-level information.
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?
For a destructive mutation, the description covers the key consequences (cascade deletion, access revocation) and the confirmation precondition, and an output schema is present. It does not explain the meaning or format of the version/idempotency parameters, but annotations and schema field names fill much of that gap.
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 should compensate by explaining parameters like expected_version, confirmation_token, and idempotency_key. It only hints at the confirmation/version concept in prose and never maps it to the actual parameters; field names alone carry the meaning.
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 names a specific action ('Delete'), a specific resource ('selected cap table and associated records'), and a distinctive condition ('after exact confirmation at the current version'). This scope clearly separates it from sibling tools like cap_table.delete_stakeholder.
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 guidance is given about when to choose this tool over alternatives such as cap_table.delete_stakeholder or cap_table.update, nor are there any exclusions or prerequisites beyond the confirmation/version condition. The usage context must be inferred from the name and sibling list.
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.
Domain prefixes (crm., cap_table., landing.) clearly separate broad modules, and most tools target a specific resource and action. However, within modules there are boundary overlaps—crm.add_contact_note vs crm.log_activity and cap_table.dilution_preview vs cap_table.simulate_raise—where descriptions must be read carefully to avoid a wrong pick.
The dominant pattern is module.verb_noun (e.g., crm.create_lead, cap_table.update_stakeholder), which is clear and readable. But a subset of top-level tools uses object_verb with flat underscores (e.g., shortlink_create, qr_generate, campaign_archive) and one outlier (campaign_stats) breaks the verb pattern, so conventions are mixed.
86 tools is an extreme surface for any single MCP server, well past the 50+ threshold that makes coherent selection impractical. Even though the features span several business domains, this would be far more usable split into focused servers per module.
The covered domains are broadly complete: cap table, CRM, incorporation, landing, projects, sparkroom, tasks, and validation all have read/write workflows with few dead ends. Minor gaps remain (no campaign listing/update, no branding palette delete/update, no contact deletion) but none of them blocks the main product workflows.