Full-text search across clause anchors, titles, and prose of a spec (core / js-api / web-api). Ranked anchor-exact > title > anchor > prose, with snippets for body matches.
| Name | Required | Description | Default |
|---|---|---|---|
| spec | No | Which spec (default core). | |
| limit | No | Max hits. | |
| query | Yes | Search text. |
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 provide readOnlyHint=true. The description adds behavioral details beyond annotations: ranking order (anchor-exact > title > anchor > prose) and snippet generation for body matches. This informs the agent of search behavior and result structure.
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 two sentences with no wasted words. The core action is stated first, followed by additional behavioral details (ranking, snippets). It is concise, front-loaded, and each sentence adds value.
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?
The description covers input (search across spec parts) and behavioral details (ranking, snippets). Without an output schema, it does not specify return fields, but the mention of snippets and ranking provides some expectation. The limit parameter suggests pagination is handled, though not explicitly detailed.
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 100% with descriptions for all three parameters. The description repeats the spec enum values but does not add meaningful new semantic information beyond what the schema already provides, meeting the baseline for fully documented schema.
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 it performs full-text search across specific parts of a spec (clause anchors, titles, prose) and names the allowed spec values. The verb 'search' and resource 'spec' are explicit, differentiating it from sibling tools like instruction_search or section_get.
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 implies usage for searching spec content, and the mention of spec values provides context. It does not explicitly state when not to use or name alternatives, but the sibling tool list (e.g., instruction_search for instructions, section_get for sections) makes the distinction clear.
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 aspect of WebAssembly: instructions (get/list/search), proposals (list), spec sections (get/list/search), version info, and types. No overlapping purposes.
All tools use consistent snake_case with verb_noun pattern: instruction_get, instruction_list, instruction_search, proposal_list, section_get, section_list, spec_search, spec_version, type_get.
9 tools is well-scoped for a WebAssembly reference server, covering instructions, specs, proposals, types, and metadata without being overwhelming.
Covers core retrieval and search for instructions, specs, proposals, and types. Minor gaps like no dedicated proposal get or type list, but the set is sufficient for typical exploration tasks.