mako_help

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

Annotations already declare readOnlyHint and idempotentHint. The description adds valuable behavioral context: 'Read-only and does not execute the returned steps.' This reinforces and clarifies the tool's non-execution nature beyond the annotations.

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 with zero wasted words. The first sentence defines the tool's purpose and inputs/outputs. The second provides usage context. Front-loaded with the primary action and result.

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?

Given the complexity (12 params, 79 siblings), the description covers the essential purpose, usage, and most inputs. The output schema exists, so return values are documented elsewhere. Missing mention of maxSteps and project identifiers, but overall sufficient.

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 0%, but the description lists many of the 12 parameters: focusFiles, changedFiles, focusRoutes, focusSymbols, focusDatabaseObjects, route, table, rpc, and the required task. However, maxSteps, projectId, and projectRef are not mentioned, providing incomplete semantics for those.

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 clearly identifies mako_help as an orientation tool that returns a Mako workflow recipe based on a task and optional anchors. It specifies the output structure (ordered tool sequence with pre-filled args) and distinguishes itself from sibling tools like reef_ask.

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?

Explicitly states when to use: before reading long AGENTS/CLAUDE docs when deciding how to start with reef_ask. Also notes it is read-only and does not execute steps, clarifying when not to use it. Could provide alternatives, but the context is sufficient.

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