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

Annotations already cover the safety profile (writable, non-idempotent, non-destructive). The description adds real context beyond that: partial-update semantics, replacement-vs-keep behavior for items, and the committed-scenario immutability constraint. Return shape is also disclosed in the absence of an output schema.

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-loaded with the key mutation semantics and immutability rule, then structured Args/Returns sections. Every sentence earns its place, with only mild redundancy between the prose and the Args block.

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 6-param mutation tool with 0% schema coverage and no output schema, the description is complete enough: it covers partial-update behavior, the committed constraint, item shape, and the return value. Nothing prevents correct invocation, though deeper detail on the item dict schema would help.

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 0%, so the description must carry the load, and it does list every parameter with meaning: name/description/strategy/extra_monthly as optional new values, items as a full replacement list whose dict shapes mirror scenario creation (add_debt/add_asset/remove). The complex items parameter is adequately explained; only granular per-field detail for the scalar args is thin.

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 (update) and resource (what-if scenario), and the parenthetical 'only the fields you pass change' immediately clarifies the mutation semantics. It does not explicitly name siblings like create_scenario or commit_scenario, but the 'what-if scenario' scope is specific enough to distinguish it from the other scenario tools.

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?

Provides a clear when-not rule ('A committed scenario can't be edited') and explains the branch between omitting items (keep existing) and passing a full list (replace). These are the two decision points an agent faces, though it doesn't explicitly route to alternatives like commit_scenario or get_scenario.

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