Heuristic readiness score for a Dev Fund proposal draft, based on attributes that correlate with approval in the historical corpus: explicit milestones, code/PoC references, sources, scope realism. Canton-specific. Not a vote; a checklist.
| Name | Required | Description | Default |
|---|---|---|---|
| draft_text | Yes | Full draft 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, idempotentHint, and destructiveHint. The description adds value by explaining the tool's heuristic nature and its limitation ('not a vote'), which goes beyond what the annotations convey.
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 concise (two sentences), front-loads the purpose, and every phrase earns its place. No wasted words.
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?
Given the simplicity (one parameter, no output schema), the description fully covers what the tool does, including the input format, the heuristics used, and the scope. It is complete for an agent to understand and invoke 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 single parameter (draft_text) has 100% schema coverage. The description adds meaning by listing the attributes (milestones, code/PoC references, etc.) that the tool looks for, which helps the agent understand what content to include in the draft_text.
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 produces a heuristic readiness score for a Dev Fund proposal draft, lists the key attributes (milestones, code/PoC references, sources, scope realism), and specifies it is Canton-specific. It distinguishes itself from siblings like 'community_consensus' by clarifying it is not a vote but a checklist.
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 implicitly guides usage by stating it is a checklist for readiness assessment, not a vote. While it does not explicitly list when-not-to-use or compare to alternatives, the context of being a heuristic makes the usage 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.
Many tools have overlapping search/retrieval functionality (search, semantic_search, full_context, search_community, search_github_issues, etc.), and the CIP-specific variants (get_cip, get_cip_history, get_cip_votes, get_cip_mentions, get_cip_citations) are numerous and subtly differentiated. Despite cross-references in the descriptions, the boundaries are fine-grained and an agent is likely to misselect among the 8+ search tools or the 8+ CIP tools.
All tool names follow a consistent verb_noun snake_case pattern (get_x, list_x, search_x, find_x). Mixed styles or camelCase are absent, and the verb choice (get, list, search, find, detect, compare) is semantically appropriate to each action, making the naming highly predictable.
With 88 tools, the surface is extremely overgrown for a single server, far exceeding the 25+ 'too many' threshold and approaching the 50+ 'extreme mismatch' category. Even for a comprehensive ecosystem knowledge base, this creates a massive selection burden and makes the tool set unwieldy for agents.
The server covers the full Canton ecosystem: docs, forum, mailing lists, GitHub, CIPs, governance, validators, versions, deprecations, security, and media. There are no glaring gaps in the knowledge domain; every major resource type has retrieval and analysis tools, making the coverage exhaustive with no obvious dead ends.