check_defined_terms

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

Beyond annotations (readOnlyHint=true, idempotentHint=true), the description adds genuinely valuable behaviors: implementation details like 'Regex-based', privacy claims 'PII-free (nothing is stored)', the raised 500,000-character input cap, and the fact that the echoed `text` is truncated to a 2,000-character preview. These are exactly the behavioral traits the agent needs to know and that the annotations do not provide.

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 description is front-loaded with a one-line scoping summary, followed by the extraction/flagging behavior and then operational constraints (regex, PII, size caps). Every sentence carries information — no filler or restatement of the tool name — and it is compact relative to the amount of useful behavior it conveys.

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?

The tool has one parameter, a fully populated input schema, a partial output schema (so return values need not be spelled out), and safe annotations. The description covers what is analyzed, what kinds of errors are flagged, input scale limits, privacy, and echo truncation behavior — nothing an agent needs to decide whether and how to invoke this tool 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 description coverage is 100%, so the baseline is 3; the description adds parameter-relevant semantics beyond the schema by disclosing the 500,000-character input cap (telling the agent it can pass an entire document in one call) and the 2,000-character echo truncation (reducing concern about huge responses). It does not rehash the schema, but enriches it with practical size constraints.

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 structure: 'extracts every term defined with `(edaspidi «X»)`', 'counts how often each is actually used', 'lists § / lõige / punkt / artiklom cross-references', and 'flags defined-but-unused or doubly-defined terms'. The opening line, 'Structural map of a long Estonian legal document', crystallizes the scope and differentiates it from sisters like tokenize, spell_check, and même check_term_consistency.

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?

Clear context exists for when to use: analysis of long Estonian legal documents/contracts, with 'Input cap is raised to 500,000 characters so a whole contract fits in one call' reinforcing the intended whole-document use case. There is a clear context, but no explicit exclusions or named alternatives, so the closely related sibling check_term_consistency is never addressed, which prevents a 5.

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