search

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered structurally. The description adds a genuine behavioral trait by noting that uql answers multi-hop questions 'with completeness' in one call. However it says nothing about subscribe/unsubscribe stateful behavior (which sits in tension with readOnlyHint=true) or about result limits, and it never explains the 'with completeness' contract in more detail.

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 short sentences with no filler, and the most actionable guidance (multi-hop → one uql call) is front-loaded. The parenthetical 'callers then tests, untested callers, impact, depth/path filters' is a compressed run-on list that slightly hurts readability but does not waste space.

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 a twelve-parameter facade fronting eleven distinct actions with no output schema, the description is thin: it does not characterize any individual action's inputs or outputs. The action=help/target_action escape hatch partially compensates by giving the agent a self-serve discovery route, but an agent must make an extra call before it can use most actions confidently.

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%, so all twelve parameters, including the action enum, are already documented in the schema. The description only reinforces the action/target_action discovery pairing, which the schema already explains. Baseline 3 applies since the schema carries the parameter burden.

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 frames the tool concretely as a 'code-intelligence (codegraph-compatible) search facade', which distinguishes it from siblings like viz, nav, edit, and structure. It names the eleven actions it fronts, but gives no per-action meaning, so the agent knows the domain and shape of the tool yet cannot infer what chain vs select vs tql_execute actually do from the description alone.

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?

It states one strong routing rule: multi-hop graph questions (callers then tests, untested callers, impact, depth/path filters) should be a single action=uql call rather than multiple hops. It also documents the discovery path (action=help with target_action). Beyond that, there is no guidance on when to use symbol vs text vs semantic vs query, and no exclusions relative to sibling tools such as nav or structure.

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