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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety is covered. The description adds genuinely new behavioral context: it discloses the return shape (titles, URLs, snippet). It omits ranking/zero-result behavior, but that's minor against the annotation coverage.

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 sentences, front-loaded with scope and the return contract, followed by the escape hatch to get_item. Examples are inline and cheap; nothing is wasted.

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 no output schema, the description correctly spells out what comes back and points to get_item for full text, which is exactly what an agent needs to chain calls. Missing only edge-case detail such as empty-result handling or result ordering.

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 description coverage is 0%, so the description must carry the load: it defines the query as keyword-based and gives three concrete examples, which is real added meaning. However the `limit` parameter is never mentioned in prose, leaving half the parameters unexplained (its default/min/max are only machine-readable).

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?

States a specific verb+resource: 'Keyword search across every case study, project and note', with concrete query examples. It also distinguishes itself from the sibling get_item, so an agent can route correctly without opening a schema.

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?

'use get_item for the full text' names the alternative and the condition that selects it, which is the key routing decision for a search tool. It doesn't cover the browse path (list_items) or say when searching is inappropriate.

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