Load one skill's FULL procedure (body) by its name or id.
Skills-first default: when the user's request matches a skill shown in
the get_context skills index or in list_skills, call this BEFORE doing
the work and follow the returned body instead of improvising.
| Name | Required | Description | Default |
|---|---|---|---|
| ref | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| error | No | ||
| inbox | No | ||
| skill | No | ||
| message | No | ||
| instruction | No | ||
| upgrade_url | 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 already cover read-only, idempotent, non-destructive behavior. The description adds useful behavioral context by clarifying the tool returns the full procedure body and should be treated as an instruction source rather than a reference lookup. It does not disclose error behavior, but the output schema mitigates the need for return-detail disclosure.
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 short sentences: the first states the core operation, the second gives the key usage rule. No filler or repetition, and the most important 'full procedure' and 'before doing the work' signals are front-loaded.
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 single-parameter, read-only retrieval tool with an output schema, the description covers the operational contract: what it loads, how to address the skill, when to call it, and how to use the result. Nothing critical is missing for an agent to invoke it correctly.
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 only provides a bare 'ref' property with no description, and schema description coverage is 0%. The description compensates fully by specifying that ref is a skill name or id, which is exactly the semantic information an agent needs to populate this single required parameter.
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 states a specific action ('Load one skill's FULL procedure (body)') and distinguishes it from list/index tools by emphasizing it returns the complete procedure, not just a skill listing. It also names the skill resource and accepted lookup keys ('name or id'), making the tool's role unambiguous.
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 an explicit when-to-use rule: call it when the request matches a skill shown in get_context or list_skills, and do so BEFORE doing the work. This is strong routing guidance that also explains why ('follow the returned body instead of improvising').
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 map cleanly to distinct resource+action pairs: projects, tasks, skills, user rules, memory, and messaging are all clearly separated. The main ambiguity is update_task versus update_task_state, since update_task can also change state and plan_status, though the descriptions do point to the narrow intended use.
The naming is largely consistent verb_noun snake_case: create_project, update_skill, delete_task, list_projects, get_context, save_turn. Minor deviations include recent_messages lacking a verb, remove_user_rule versus delete_* style, and singular user_rule in mutations versus plural user_rules in listing.
With 27 tools, the server is over the typical well-scoped MCP range, even though it covers several domains. Some consolidation is possible, such as folding update_task_state into update_task and reducing the overlapping retrieval/search tools.
The tool set provides strong lifecycle coverage for projects, tasks, skills, and user rules, plus memory retrieval, agent messaging, and onboarding help. Minor gaps exist, like no standalone get_task or list_tasks and no explicit inbox listing, but get_project and get_context largely cover those needs.
