Add, change, move or remove a recipe line

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

With no annotations, the description carries the full burden and does: references are checked first, the result reads every line back, the console re-cooks an edited line itself (MergeLowPriority), a removed line's output disappears, and coverage is reported before/after (autoCooked). enabled:false preventing an initial cook is a non-obvious side-effect 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?

Front-loads the purpose, then organizes the body by action (add/set/move/remove) so each clause earns its place. It is dense and long-winded in places, but content-rich rather than padded.

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 11-parameter, nested-object, no-annotation tool with no output schema, the description covers mutation side effects, verification/return behavior, prerequisites, and scope limits. An agent has what it needs to call it correctly.

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?

At 64% schema coverage the description adds real meaning beyond the schema: it maps which fields belong to which action, explains values:null clears values, enabled:false switches a new line off before cooking, and preview returns planned commands. It leaves 'name' and the general 'target' object largely unexplained, so it is not fully compensating.

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 set (add/set/move/remove) and an exact resource: 'one standard recipe line of a preset or cue part'. It also names the sibling boundary (gma3_cook_recipes) and the scope exclusions (phaser lines, filters, timing), so an agent can distinguish it without opening the schema.

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?

'The target must exist' is an explicit prerequisite, and it routes the agent to gma3_cook_recipes when immediate cooking with Merge/Overwrite/Remove is wanted. 'Phaser lines, filters and timing columns are not edited by this release' is an explicit when-not, and preview:true is offered as the dry-run path.

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