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

Annotations already provide readOnlyHint=true and openWorldHint=false, so the description adds value by specifying sorting by relevance and cursor-based pagination. It does not contradict annotations. It could mention other traits like no side effects, but given annotation coverage, this is sufficient.

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?

Two concise sentences. The first sentence defines the action and scope, the second provides usage guidance and pagination detail. Every sentence earns its place; no redundancy or fluff. Front-loaded with key 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?

With 2 parameters, no output schema, and existing sibling tools, the description covers the essential behavior (search, relevance, pagination). However, it does not describe the return format or fields of each component in the results. While paginated by cursor is mentioned, an agent might need to know what fields are returned to use the result 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?

Schema coverage is 100% with both parameters documented. The description adds meaning beyond schema: it explains cursor is for pagination and query is natural language terms. It also mentions sorting by relevance, which is not in the schema. Baseline 3 is increased due to these additions.

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 specifies the tool's verb ('Recherche'), resource ('composants'), and scope (free text on name, description, category, tags, sorted by relevance). Examples like 'tableau triable', 'graphique' provide concrete usage. It effectively distinguishes from siblings: get_component (single), list_components (list all), suggest_composition (composition).

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 explicitly states when to use this tool: 'À UTILISER quand on cherche un composant par fonction ou mot-clé'. It provides context and a clear use case. It lacks explicit when-not-to-use, but the presence of sibling tools (get_component, list_components) implies alternatives, though not directly stated.

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