Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=false, so the description doesn't need to state that it's read-only. The description adds meaningful behavioral context beyond the schema: it explains that server install snippets include local (stdio via npx) for every published server and remote (HTTP) when a hosted endpoint exists, and how the `client` parameter influences output (one client vs all). There is no contradiction with annotations, and the openWorldHint=false is consistent with the enum-constrained `kind` and `client` parameters.

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, well-structured paragraph of three sentences that front-loads the core purpose, immediately explains the tool-vs-server distinction, and then details output variations. Every sentence earns its place; there is zero fluff or redundant restating of the title or annotations.

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 tool's moderate complexity (3 parameters, 2 enums, output schema present), the description is nearly complete: it covers purpose, scoping, and output shape. The only minor gap is that it doesn't spell out what exactly the 'description' field contains for a server or tool, but the output schema presumably covers return values. Since an output schema exists, the description doesn't need to explain return values in depth, so this is quite complete.

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% and includes detailed parameter descriptions, so the baseline is 3. The description adds value by elaborating on what the returned output contains per kind and client, and by explaining the auto-detection logic for `kind` (underscores vs hyphens) which reinforces and extends the schema description. It clearly maps the `client` parameter to the behavior of limiting output. This goes beyond the schema, warranting a 4.

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 uses a clear verb-resource structure ('Return the description and install snippets') and explicitly distinguishes behavior for tools vs servers, which differentiates it from its only sibling tool (cyanheads_search_catalog, which discovers names). It is immediately clear what this tool does and what class of objects it operates on.

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 and parameter schema provide explicit usage guidance: the `kind` parameter explains when to set it vs auto-detect, and the `name` parameter explicitly says to use cyanheads_search_catalog to discover valid names. This is an explicit when/alternative routing (sibling tool for discovery, this tool for retrieval) and clarifies optional vs required parameters.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.