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

Annotations already declare readOnly, idempotent, non-destructive, closed-world — so the safety profile is fully covered. The description adds that the result is computed 'por código' (i.e., against codified CPC brackets) and that it carries 'fundamento e premissas' (legal basis and stated premises), which is genuine added context about the nature of the output, but it does not describe rounding, ranges of the fee brackets, or failure behavior.

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 short sentences, front-loaded with the object of calculation, no filler or repetition. Slightly terse to the point of obscurity in 'por código', which costs it the top mark.

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 three required parameters, no output schema, and low schema coverage, the description should do more: it omits how base and party interact, which CPC bracket applies to public_treasury versus labor, and what the 'premissas' actually contain. What it does say (CPC percentages, code-driven, returns basis and premises) is directionally complete for a read-only calculator, but leaves meaningful gaps for correct invocation.

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 description coverage is only 33%: fewer than half the parameters are documented, and the description mentions no parameter at all. It never explains what 'base' is (condemnation amount? post-liquidation value?), what the 'party' enum values private/public_treasury/labor imply for the applicable CPC bracket, or why 'date' is mandatory only against the Fazenda — the very thing that decides which regime 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?

States a specific legal computation: 'Honorários advocatícios de sucumbência pelos percentuais do CPC' — verb (calculate), resource (loser-pays attorney fees), and governing standard (CPC percentage brackets). It is clearly distinguishable from siblings like claim_value_calculate or alimony_value_calculate, though it never names an alternative explicitly.

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 explicit when-to-use/when-not guidance and no reference to any sibling calculator, despite a large family of overlapping 'calculate' tools. The only usage signal is implicit domain framing ('sucumbência', 'CPC percentages'), which an agent must infer.

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