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

Annotations declare destructiveHint=true and idempotentHint=true, and the description goes well beyond them: unmarking a goal keeps the funnel and its history, a fixed amount retroactively applies to past days, while detail-based revenue counts only from the day it is set, and there is a 5-goal-per-project cap where a goal still consumes a funnel slot. It does not mention permission requirements or what the response body contains, which is the remaining gap for a destructive mutation.

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?

It is front-loaded with the mutation scope before the caveats, and nearly every sentence carries needed information. The cost is that it is one dense paragraph with the goal_value and run_id material interleaved, which makes it slower to scan than a bulleted or separated form.

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 destructive, multi-mode mutation with no output schema, the definition covers the side effects (retroactive revenue, history retention), the goal cap, the currency format, and the run_id lifecycle including the returned id. An agent has everything needed to call it correctly, or to route to create_funnel when steps must change.

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 already 100%, but the description still adds real meaning: goal_value's three kinds and their retroactivity rules, that amounts are decimal strings in the project currency (get_project), the 'never ""' constraint on run_id, and the run_id return value that should be threaded into later changes. This is genuine semantic value rather than restatement.

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 opening clause names a specific verb (change) and the exact mutable fields (name, is_goal, goal_value) and immediately scopes it with 'what you omit stays'. It also distinguishes itself from create_funnel by stating 'Steps and trait_scope never change: a different step means a new funnel', so an agent can separate update from create without opening sibling schemas.

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 gives explicit when/when-not rules: use this to rename or toggle goal status, but not to change steps (make a new funnel instead). It also spells out the run_id branch — pass it from start_setup_run for undoable setup work, omit it (never empty string) to start a new chat run — and points to list_sources, list_campaigns, and get_project for the data needed to set goal_value.

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