search_bus

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds the meaningful trait that an empty query flips the tool into a browse mode and that multi-table defaults differ, but says nothing about result ordering, scoring, or what withholding of cross-client results looks like.

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?

Three dense, zero-padding sentences with the core action front-loaded. It is arguably too terse in places ('Set tables param for multi-table'), trading a little clarity for compactness, but no sentence 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?

For an 8-parameter, multi-mode search tool with no output schema, the description covers modes and browse behavior but not result shape, ranking, or how cross-client withholding resolves. Adequate as a starting point, incomplete for an agent that needs to interpret output.

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%, so every parameter (including mode values, limit clamping, and category being browse-only) is already documented in the schema. The description restates mode values and the tables param without adding format or interaction detail beyond what the schema provides — baseline 3.

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 (Search) and resource (knowledge and/or handoffs), and names the mode dimension. It never distinguishes itself from siblings like list_handoffs or get_handoff, so an agent must infer that this is the ranked/query-based retrieval path rather than the enumerate-one path.

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?

Gives real conditions for the browse path ('Empty query or "*" browses recent entries') and for multi-table via the tables param, but offers no guidance on when to choose this over list_handoffs/get_handoff, nor any exclusions. Usage is implied by mode semantics rather than stated as routing advice.

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