Create an audited export receipt for an approved artifact or internal draft. External publish remains separate and human-approved.
| Name | Required | Description | Default |
|---|---|---|---|
| format | No | ||
| target | Yes | ||
| draft_id | No | ||
| tenant_id | Yes | ||
| artifact_id | No | ||
| target_config | No | ||
| idempotency_key | No | ||
| approval_event_id | No |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / properties / target / enumPrevious value: -[
- "markdown",
- "html",
- "email_draft",
- "linkedin_draft",
- "cogentcast_content",
- "talent_scout_workspace",
- "json"
-]New value: +[
+ "markdown",
+ "html",
+ "email_draft",
+ "linkedin_draft",
+ "cogentcast_content",
+ "talent_scout_workspace",
+ "json",
+ "pdf",
+ "docx"
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotation Contradiction: the description opens with 'Create' and describes producing an audited receipt, implying a state-changing operation, while the readOnlyHint annotation is true. The sentence about external publish does not resolve whether this tool writes an audit/export record; the schema's idempotency_key further suggests mutation. This is a serious inconsistency.
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, front-loaded with the main action, and no filler. Every clause 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?
With 8 parameters, nested objects, and 0% schema descriptions, the description leaves too much to inference: which ID to supply, what target_config contains, and what idempotency/approval fields mean. An output schema exists, but that only handles the return side, not call construction.
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 must compensate for parameters. It only hints that artifact_id or draft_id corresponds to 'approved artifact or internal draft' and gives no semantics for target_config, idempotency_key, approval_event_id, format, or target beyond the enum names.
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 and resource: 'Create an audited export receipt' and scopes it to 'an approved artifact or internal draft.' It also separates this from external publish, which helps distinguish it from publish/approval-related siblings, though it does not name them.
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?
It clearly says the tool is for approved artifacts or internal drafts, and states external publish is out of scope and human-approved. It does not explicitly name alternatives like artifact_generate or artifact_save, but the use case is sufficiently bounded.
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 exact duplicates (talent_scout_my_profile_status and talent_scout_profile_status have identical descriptions), and eight estimator_estimate_* tools share the same generic description with no differentiation. This will cause misselection.
Most tools follow a snake_case verb_noun pattern, but there are inconsistencies: the duplicate profile tools have different naming (my_profile vs profile), and `fetch`/`search` are single-word verbs. Predictability is hampered by these deviations.
65 tools is excessive for a coherent set, especially with many tools covering overlapping actions across multiple unrelated domains (AI receptionist, estimator, talent scout, GrowthOS). The count could be trimmed significantly.
The tool surface is broad and covers many lifecycle operations (create, read, export, record), but the duplicate tools and identical descriptions for estimator operations make it unclear whether all needed operations are present. Some expected operations like delete/update are missing for certain resources.