Store one small inert text, JSON, patch, or log candidate; nothing is executed.
| Name | Required | Description | Default |
|---|---|---|---|
| artifact | Yes | ||
| work_item_id | Yes | ||
| idempotency_key | Yes |
| 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?
The description adds valuable context beyond the annotations by explicitly stating 'nothing is executed' and 'inert,' clarifying that storing does not trigger side effects. This is compatible with the idempotentHint and readOnlyHint=false, adding nuance that the operation is a write but not an execution. No contradictions.
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, well-structured sentence that front-loads the verb and object, states allowed types, and ends with a crucial safety qualifier. Every part earns its place; no fluff.
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 tool with a complex nested schema and three required parameters, this description is underspecified. It does not explain the role of work_item_id or idempotency_key in the submission workflow, the purpose of evidence_urls, or what happens to a stored candidate. The output schema exists but the overall workflow context is missing.
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 description mentions the artifact kinds (text, JSON, patch, log), but this only restates the enum values already present in the schema. It provides no additional meaning for work_item_id, idempotency_key, metadata, or evidence_urls. With 0% schema description coverage, the description fails to compensate for the undocumented parameters.
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 identifies the action as storing a candidate, explicitly enumerates supported content types (text, JSON, patch, log), and adds the crucial clarification that nothing is executed. This distinguishes it from execution or review tools, matching the name and separating it from siblings like review_candidate.
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 gives no explicit advice on when to use this tool vs alternatives. It does not mention that this is for creating candidates for later review, nor does it reference sibling tools or exclusions. The 'nothing is executed' hint implies it's not for running content, but this is not framed as a usage guideline.
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.
Each tool targets a distinct resource and action: problem lifecycle, knowledge reading/search/context, candidate submission/review, and experience verification. Even similar tools like get_knowledge, search_knowledge, and retrieve_context are clearly differentiated by their descriptions.
All tool names follow a consistent snake_case verb_noun pattern with no mixed conventions or vague verbs. Names accurately reflect their actions and objects, making the set predictable and easy to navigate.
At 16 tools, the count is slightly above the typical 3-15 range but still reasonable given the multi-faceted domain (problems, knowledge, candidates, experiences). Each tool appears to have a specific purpose, though a few could potentially be consolidated.
Core workflows are covered: create/claim/manage problems, submit/review candidates, publish/retrieve knowledge, and verify experiences. Minor gaps exist such as no explicit close/cancel operation for problems, but agents can work around these with existing tools.