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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the description's job is to add calculation context — and it does, laying out the full pipeline (position salary, category, supervision, notebook checks, rural/master supplements, then OPV/VOSMS/IPN withholdings to net) and disclosing that the cabinet-manager rate is 'not confirmed against a primary source'. It does not cover output shape or rounding/output-schema behavior, which keeps it out of 5 territory.

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 purpose and calculation flow are front-loaded, which is good, but the body is one enormous run-on paragraph enumerating every enum id inline. Given that the schema defers to the description, the content is largely earned, yet a bulleted or grouped structure would be far more scannable — as written it is bloated prose.

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 13-parameter, no-output-schema, single-shot calculator, the description covers the model inputs, supplement logic, and the gross-to-net stages so an agent understands what it is invoking. The main gap is that it never states what the returned result contains numerically (rate breakdown vs. a single figure), forcing the agent to infer the output.

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 nominally 100%, but the schema descriptions for experience_id, category_id, curator_id and notebook_check_id simply say 'see tool description' — so the description is the only place the enum semantics live, and it supplies every id with its Russian label and percentage rate. That is genuine added value, though parameters such as lang, weekly_hours, standard_hours and is_small_class get no elaboration beyond their schema text.

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 verb and resource ('Calculates the monthly salary of a Kazakhstan state-school teacher in 2026') plus the legal basis (Decree No. 1193, Law 'On the Status of the Pedagogue'). This clearly distinguishes it from the generic siblings kz_salary_gross_to_net and kz_salary_net_to_gross, which do not model teaching supplements.

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 operational usage guidance: the id-based options 'are fixed ids; ask the user which applies and do not guess', which tells the agent how to source parameter values. It does not explicitly say when to prefer this over the generic gross-to-net siblings, so it stops short of full when/when-not routing.

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