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

Annotations already declare a mutation (readOnlyHint=false, destructiveHint=true), so the bar is lower, and the description still adds meaningful behavior: the authorization model, the project-owner-only restriction on markup, and that passing null on the task removes it. It does not explain partial-update semantics (whether omitted fields are left untouched) or reversibility.

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 front-loaded sentences: the operation and field list first, the permission model second. Dense but every clause adds information; only the task/cardId mismatch introduces noise.

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 9-parameter mutation with 33% schema coverage and no output schema, the description covers precondition, permissions, and the field list reasonably well. It still leaves gaps an agent needs: partial-update behavior, the undocumented cardId field, and the phantom 'task' parameter.

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 only 33%, so the description carries extra burden; it does enumerate the mutable fields (description, amount, day, category, vendor, billable, markup, task), which adds value. However it omits the cardId parameter entirely and references a 'task' argument that does not appear in the schema, creating confusion about the actual parameter set.

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 and resource ('Changes an expense') plus a scoping condition ('that is not yet on an invoice'), which cleanly separates it from create_expense, delete_expense and list_expenses. It stops short of naming a sibling explicitly, so it is clear but not fully differentiated.

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?

Gives an explicit precondition ('not yet on an invoice') and states who is permitted to perform the change (logger or project owner, with markup restricted to the owner). That is real when-to-use context, though it never says what to do instead when the expense IS already on an invoice or points to an alternative tool.

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