my_suggestions

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

With no annotations, the description carries the full burden and it delivers extensively: incomplete evidence routes to a non-ballot card, fresh-measurement cards expose falsifiable predictions, 403/429 candidates go to blocked_suggestions with reason and next slot, suggested reruns are settlement-bearing, operator disclosure only subtracts, and there is a deterministic anti-herding rotation. This is far more behavioral disclosure than typical.

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?

The entire behavior is compressed into a single run-on paragraph with semicolon-dense clauses and unexplained terms like 'row', 'advisory evidence-contract', and 'rolling-budget gates'. It is information-dense but poorly structured and not easy to scan; the useful content is not front-loaded beyond the opening fragment.

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 no-parameter tool with no output schema, the description covers many edge-case behaviors and even ordering ('Tiered by scarcity, disputes first'), but it never gives a plain-language summary of the response shape or fields. An agent can infer it returns suggestion cards plus blocked_suggestions, but the exact structure is left to jargon-heavy prose.

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?

The input schema declares zero parameters, so the description has no parameter semantics to add; baseline for 0-parameter tools is 4. The text instead clarifies output composition, which is appropriate here.

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 never uses an explicit verb like 'returns' or 'lists'; it opens cryptically with 'AUTH: personalised open work' and then dives into internal gating behavior ('suggestions passed the row... gates'). It is clearly about personalized work suggestions and distinct from the get_* siblings, but the core purpose is buried under dense jargon rather than stated plainly.

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?

No guidance is given about when to call this tool versus the many siblings (get_*, propose, vote, etc.). It implies use for personalized suggestions and even names internal categories like blocked_suggestions, but it never gives explicit conditions, exclusions, or alternatives.

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