Build a thematic corpus from observations filtered by type, tags, or symbol to give AI assistants focused, symbol-aware code context.
Build a thematic corpus from observations filtered by type / tags / symbol.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Unique per project. | |
| project | No | Project name/path (default: active). | |
| filter_tags | No | ||
| filter_type | No | ||
| filter_symbol | No |
Changes observed during successful MCP inspections.
v4.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare this is a non-readOnly, idempotent, non-destructive, closed-world write, so the safety profile is covered. The description adds the scope of what is included (type/tags/symbol) but says nothing about persistence, what happens when the name already exists, or whether an existing corpus is overwritten or fails.
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 with no wasted words. It is efficient, though arguably under-specified rather than merely concise given the five-parameter schema.
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 five-parameter write tool with no output schema and only 40% schema coverage, one sentence is thin. It omits how filters combine, the project/active-project prerequisite, error behavior on duplicate names, and any relationship to corpus_query, leaving an agent without enough to invoke it confidently.
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 coverage is only 40%: filter_tags, filter_type, and filter_symbol have no schema descriptions. The description partially compensates by mapping 'type / tags / symbol' to those three parameters, but it gives no combination semantics (AND/OR), value formats, or default behavior for the project 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?
States a specific verb ('Build') and resource ('thematic corpus'), plus its input source ('observations') and filter facets. It is distinguishable from the 'corpus_query' sibling by verb, though the description never explicitly contrasts the two.
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 filtering facets imply the context (create a corpus from filtered observations), but there is no explicit when-to-use guidance, no mention of the paired 'corpus_query' tool, and no prerequisites such as project context or required permissions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.