common_legal_usage

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

Even with readOnlyHint and idempotentHint annotations, the description adds meaningful behavioral context: results are corpus-bounded, non-prescriptive, derived from an offline index, and gated on ESTNLTK_MCP_LEGAL_INDEX for the full corpus. This clearly tells the agent what kind of signal it is receiving and its limitations.

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 the core purpose and uses concrete examples effectively. The final 'Input is a single word' is helpful but redundant given the schema, and a slightly tighter version would be possible without losing value.

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?

Given the single parameter, available annotations, and existing output schema, the description covers everything needed: what the tool returns, how it behaves, its limitations, its intended role, and how the corpus index is configured. There are no meaningful gaps for an agent to misuse this tool.

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?

The input schema already fully documents the 'word' parameter with examples and coverage at 100%, so the baseline is appropriate. The description reinforces 'Input is a single word' and supplies examples, but it does not add substantive semantic details beyond what the schema already provides.

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 clearly identifies the tool as returning canonical legal collocations for a term, with an explicit mechanism: term frequency plus neighboring words in Estonian legal text. Concrete examples ('hagi' → 'esitama hagi') anchor the meaning and make it easy to distinguish from siblings like synonyms or related words.

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?

The description states when to use the tool: when the AI needs real, idiomatic legalese rather than invented collocations. It also gives important caveats about the corpus being proof-of-concept and not prescriptive, but it does not explicitly name alternatives or say when not to use it.

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