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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so safety needs no restating. The description adds useful content scope, notably that results include status and sources for tracked cases, but says nothing about volume, freshness, or whether 'distance to 61' is a count or a margin.

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 a single sentence with no filler, but it is a dense parenthetical pile-up that buries the primary subject behind two competing topic clusters. Front-loading the 'what changes' computation ahead of the complaints list would help.

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?

With no output schema, the description must carry return semantics, and it does sketch the fields returned. However, terms like 'distance to 61' and 'nearest seat each way' remain unexplained, so an agent cannot fully predict response shape or units.

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?

Only one optional parameter (lang) with a fully covered schema description including the enum and the 'default en' note. The description adds nothing about language handling, but with 100% schema coverage the baseline of 3 applies.

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 does enumerate the content returned (seat-change votes, bloc distance to 61, nearest seats, tracked complaints/inquiries/cases/appeals), but the tool name 'get_what_can_change' is abstract and the sentence fuses two unrelated data sets (electoral arithmetic and case tracking) without saying what the resource actually is. An agent can guess the payload but cannot confidently distinguish it from check_coalition or get_formation.

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?

There is no statement of when to call this versus the clearly related siblings (check_coalition, get_results, get_formation), and no prerequisites or exclusions. The agent must infer usage entirely from the payload list.

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