Create or update a prospect/lead. Actions: create — new prospect (name + at least one contact) update — edit an existing prospect (requires id_prospect)
[Flattened action: update]
| Name | Required | Description | Default |
|---|---|---|---|
| data | No | ||
| name | No | ||
| No | |||
| phone | No | ||
| account | No | ||
| id_branch | No | ||
| id_prospect | No |
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 indicate the tool is not read-only (readOnlyHint=false), and the description implies mutation. It does not contradict annotations. However, the description does not add much beyond the annotations; it does not disclose potential side effects, permissions, or what happens on update (e.g., partial vs full overwrite). With no additional behavioral context, the score is at baseline.
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 concise, with a clear action list and a note about flattened action. It is front-loaded with the primary purpose and quickly explains the two actions. The exclusion of the bracket note 'Flattened action: update' might be confusing, but it does not add much length. Overall, it is efficient but could be slightly clearer.
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?
Given the tool has 7 parameters, no output schema, and moderate complexity (nested object), the description is insufficient. It does not explain the 'data' parameter, the expected return format, or any business rules beyond the basic create/update distinction. Annotations are minimal, so the description should provide more guidance, but it falls short.
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?
The schema has 7 parameters with 0% coverage, but the description explains that 'id_prospect' is required for update and that create requires 'name + at least one contact'. This adds some meaning to parameters. However, it does not explain the 'data' parameter (which is a nested object and likely critical for action details), nor does it clarify the distinction between 'name', 'email', 'phone' vs the 'data' object. Given the low coverage, the description should compensate more, but it only partially does.
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 that the tool creates or updates prospects/leads, and it distinguishes between create and update actions. It explicitly mentions that 'update' requires id_prospect, which helps differentiate from the sibling tool evo_prospect_write_create. However, it could be more explicit about the resource being 'prospect' and the scope, but overall it is clear.
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 provides some usage guidance: it explains when to use create vs update (create for new prospects, update for existing with id_prospect). However, it does not explicitly compare with alternatives like evo_prospect_write_create or evo_prospect, nor does it specify when not to use this tool. The guidance is present but minimal.
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.
Several tools are duplicated with nearly identical descriptions, distinguished only by a '[Flattened action]' footnote (e.g. evo_activity_list vs. evo_activity_schedule, evo_member_get vs. evo_member_list, evo_prospect_write_create vs. evo_prospect_write_update). An agent would struggle to pick the correct one without parsing fine-print labels. authenticate and connect also blur the auth boundary.
The EVO tools use a rough 'evo_<noun>_<action>' pattern but mix verb positions and styles: evo_member_get, evo_list_accounts, evo_activity_schedule, evo_sales_create, evo_bank_accounts. Platform tools like authenticate, connect, report_bug, and marketplace abandon the evo_ prefix entirely, and the giant marketplace tool follows no naming convention.
26 tools is above the 15–25 'heavy' band, and several are redundant flattened variations that should be merged. The set also mixes domain-specific EVO tools with unrelated platform utilities (marketplace, toolkit_info, report_bug), inflating the count without coherent coverage.
The domain is gym management (members, activities, prospects, sales, receivables), but the surface has major gaps: no member create/update/delete, no activity-create or schedule management, and only partial write operations elsewhere. Some tools contain unresolved 'PROBE' prompts, indicating unfinished endpoints that agents cannot reliably use.