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

Beyond the read-only, idempotent annotations, the description discloses what each record contains (why, monthly saving, approve link), that ordering is 'most valuable first' for waiting but 'newest first' otherwise, and what the status buckets actually mean (active = approved/running/7-day watch; done = kept, undone, declined, expired, failed). That is substantive behavioral context an agent cannot get from the annotations or 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?

It is compact and front-loads the resource and default status before the enum detail. The phrasing is dense and slightly run-on ('Changes Taseli prepared and is waiting to make', the trailing 'except waiting'), costing some readability but not wasting whole sentences.

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 filtered, paginated list with an output schema, the description covers the important unknowns: what an item includes, ordering rules, status semantics, and the owner-approval constraint. Pagination behavior and the account/language parameters are left to the schema, which is reasonable given an output schema exists.

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 100%, so the baseline is 3, but the description adds genuine meaning by expanding the status enum into lifecycle states and by explaining that sort order differs between waiting and the other statuses. The limit, cursor, account and language parameters get no additional prose, which is acceptable since their schema descriptions are already complete.

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 states a specific verb and resource: it lists 'Changes Taseli prepared and is waiting to make', with what each item carries (why, monthly saving, approve link). An agent can tell this is a paged list of pending change proposals, distinct from singletons like get_decision. It stops short of explicitly naming the sibling to use for a single decision, 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?

It gives clear operating context: 'Only the owner approves, in Taseli', which tells the agent this tool reads and cannot approve, and where the human action happens. The status menu (waiting default, active, done, all) with lifecycle meanings further guides selection. It does not explicitly say when to prefer get_decision over this list, so it stops at clear context without named alternatives.

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