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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower; the description earns credit for disclosing the ingestion-vs-origin trap, Chile-only coverage for by=origin, and that null keys are a coverage gap rather than an 'unknown' category. It does not mention result ordering, bucket limits, or what happens with no filters applied.

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 purpose and the list_bills contrast before diving into per-value caveats, so an agent can stop reading early if it just wants the gist. The null-bucket explanation is stated twice (once for origin, once at the end), which is the one redundant beat.

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?

An output schema exists, so return shape needn't be described; the description instead covers the non-obvious risk in a grouped aggregate — trusting a bucket label. With zero required params and 100% schema coverage, nothing an agent needs to invoke this correctly is missing.

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 real meaning to the enum beyond the schema's bare list: status is resolved to the latest tramitación's state, type to ley ordinaria/acto legislativo, source to ingestion origin, and origin to Moción vs Mensaje with an explicit 11-country coverage caveat. That is substantive disambiguation of the one parameter that determines the whole result.

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 precise verb+resource: counts of bills bucketed by one dimension, scoped to any filter list_bills accepts. It explicitly contrasts itself with list_bills by noting the alternative is paging every matching row and tallying by hand (4,088 rows at 50/page), which lets an agent pick the right tool without opening a schema.

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 concrete triggering questions ('¿cuántos se aprobaron?', '¿cuántos por tipo?') and names the sibling it replaces. It also states the condition under which a specific group-by is misleading ('source is where Dapper ingested the record, NOT the bill's constitutional origin') and points to the correct alternative (by=origin, Chile only).

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