alternativesCurated alternatives to a library, each with a one-line "prefer it when" and a verdict if the alternative is also indexed.
| Name | Required | Description | Default |
|---|---|---|---|
| library | Yes | Library name as published on npm or PyPI |
| Name | Required | Description | Default |
|---|---|---|---|
| answer | Yes | The clamped text answer (hard limit ~500 tokens) |
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 declare readOnlyHint=true and destructiveHint=false, covering the safety profile. The description adds value by explaining the output structure: alternatives are curated and include a one-line 'prefer it when' and a verdict if indexed, giving the agent concrete expectations about what will be returned.
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, dense sentence that states the core function and key output details without unnecessary words. It is front-loaded with 'Curated alternatives' and efficiently packs useful information.
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 simple one-parameter tool with an output schema (as indicated), the description provides sufficient context. It covers the main output elements (prefer-it-when, verdict) and relies on schema and annotations for the rest, making it complete for an agent to select 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 input schema fully describes the only parameter 'library' with its format (npm or PyPI). The tool description adds no extra parameter details, but since schema coverage is 100%, the baseline of 3 applies without requiring compensation.
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 specifies the tool provides curated alternatives for a library, including a one-line 'prefer it when' and a verdict if the alternative is also indexed. This clearly distinguishes it from siblings like pick_library or should_i_use, which focus on selection or evaluation.
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 the use case (finding alternatives to a library) but does not explicitly state when to use it versus sibling tools or when not to use it. There is no mention of alternative tools like pick_library for choosing or audit_dependencies for security checks, so guidance is inferred rather than direct.
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 phase: deciding on a library (should_i_use, pick_library, alternatives), learning usage (how_do_i, docs_link), and auditing existing dependencies (audit_dependencies). There is no meaningful overlap between any two tools, as they clearly differentiate by input (task vs. library) and output (recommendation vs. snippet vs. docs).
The names are all snake_case but mix imperative verbs (audit_dependencies, pick_library), nouns (alternatives, docs_link), and question phrases (how_do_i, should_i_use). This makes the set readable but not predictably patterned; an agent cannot anticipate a consistent verb_noun structure.
Six tools is well-scoped for a library advisory server, covering selection, verification, documentation, usage, and dependency auditing without redundancy. The count is within the ideal range and each tool serves a distinct purpose.
The tool set covers the full lifecycle: pick a library (pick_library), evaluate it (should_i_use), see alternatives (alternatives), get usage snippets (how_do_i), get official docs (docs_link), and audit a project's dependencies (audit_dependencies). There are no obvious dead ends for common library decision workflows.