compile_flow

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

Annotations only declare readOnlyHint=true; the description adds genuine behavior: it populates uids in the flow and, when a name fails to bind uniquely, returns candidate matches instead of erroring. 'Does not act' reaffirms the read-only safety profile and is consistent with the annotation. No contradiction present.

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?

Four short sentences with zero waste: the core operation first, the mechanism second, the constraint third, and the negative scope last. Every sentence earns its place and the most decision-relevant information is front-loaded.

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?

The essentials for a read-only compile tool are present: input (a run_flow), purpose (fill uids against the live outline), failure mode (candidates on ambiguous names), and absence of side effects. The gap is that the success return value is only implied by 'fills uids' with no output schema to fill the void, and requireExpect remains unexplained.

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?

The schema has 0% description coverage and its parameter names (steps, requireExpect) carry little meaning on their own. The description adds domain context — that steps is a run_flow whose names must bind against the live outline — which clarifies the main parameter. But requireExpect is left entirely unexplained, so compensation for the schema gap is only partial.

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 ('Compile'), a resource ('a run_flow against the live outline'), and the operation's effect ('Fills uids'). The closing 'Does not act' draws a clear line against the sibling run_flow, which exists to execute. The purpose is immediately identifiable.

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?

'Does not act' communicates the boundary to run_flow, the obvious execution sibling, telling the agent this tool prepares a flow rather than runs it. The unique-binding condition also tells the agent what input state is required for a clean compile. However, it never names run_flow or states explicitly 'use run_flow when you want execution,' so the routing is implied rather than spelled out.

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