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

No annotations are provided, so the description carries the full burden and does well: it declares 'Read-only', explains the score (0-1, merge order), discloses degraded=true on type failure/denial, skipped_by_kind on filtered-out types, and that the cursor is opaque. It omits auth requirements and any rate/volume limits, which keeps it short of a 5.

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?

Front-loaded with the core verb and resource in the first sentence, then detail. Some waste: the enumerated hit fields (kind, id, title, subtitle, href, score...) duplicate the output schema and could be trimmed.

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 an 8-parameter federated search with a 100%-covered schema and an output schema, the description covers the remaining gaps an agent needs: read-only nature, ranking semantics, cursor reuse, degraded and skipped_by_kind signals. Nothing essential to correct invocation is missing.

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 100% (8 params, all documented), so the baseline is 3. The description's only added parameter value is reiterating that ranking/cursor match the console and /v1/search, which is marginal beyond what the schema already says about query tokens, cursor, and skip behavior.

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 and resource ('Find objects of any type by name or text') plus the scope of the result set ('ranked on one list'), which distinguishes it from the per-type siblings (work_list, file_list, project_list, memory_recall). It never names those alternatives explicitly, so the cross-type vs per-type distinction is left to inference.

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?

Usage context is only implied: 'any type', the console palettes, and GET /v1/search tell an agent this is the broad federated search, but there is no explicit when-to-use / when-not-to-use statement or named alternative. An agent must infer that it should prefer this over the typed list tools.

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