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

Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=false), but the description adds real behavioral context: it discloses that it returns yearly/monthly/quarterly figures plus their inputs and a limitations field, and warns to read data.limitations before quoting. That epistemic framing (public-text estimate, not tax advice) is valuable beyond the annotations.

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?

Purpose and scope are front-loaded, and every sentence carries information (formula, inputs, outputs, limitations, disclaimer). The middle sentences are somewhat long and clause-heavy, but there is no filler or repetition of the name/title.

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 carries the return-value burden and does so — it names the yearly/monthly/quarterly outputs, the figures used, and the limitations field. For a read-only estimator this is nearly complete; only error paths (e.g. country_not_available, handled in the schema) and rate-availability caveats could be added.

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 100%, so the schema already defines lang, year, regime, country and revenue. The description adds only marginal semantics beyond that (the rate-on-a-base formula, floor/ceiling indexed on SNMG), which explains the model rather than the parameters themselves, so the baseline 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 states a specific verb and resource ('Estimate the yearly contribution to CASNOS'), names the domain (Algerian social security fund for the self-employed) and pins the year to 2026 with the exact formula used. An agent can distinguish it from calculate_ifu or get_social_contributions without opening the schema, since those are other levies/other data sources.

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 calling guidance ('Give the regime and, for most regimes, the amount') and clearly signals this is an estimate, not legal advice, which frames appropriate use. However, it never states when to prefer this over siblings like calculate_ifu or get_social_contributions, nor any exclusion conditions, so usage is implied rather than spelled out.

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