match-glossary

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It explicitly states that it writes translations.json and reports unmatched strings, which covers key side effects. However, it does not disclose whether existing files are overwritten, what the unmatched string report looks like (logged, returned, or written), or any error/failure behavior. This is adequate but lacks depth for a file-writing operation.

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 two sentences, front-loaded with the core purpose first and the output/reporting second. Every phrase adds value: 'previously extracted' anchors the pipeline, and 'ready for apply-text-translations' clarifies the output's purpose. There is zero fluff or tautology.

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 or annotations, the description must convey more context but does only partially. It explains the core workflow and mentions the output file, but it does not elaborate on the format/content of translations.json, the nature of unmatched string reports, or edge cases like empty matches. These omissions leave an agent uncertain about what exactly will happen when called.

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 100%—both parameters have descriptions in the schema, so the description adds minimal extra meaning. It reiterates the 'English | Vietnamese' table detail already present in the schema's docxPath description, and the 'previously extracted' context is a slight addition. Under the schema-heavy baseline, this does not exceed the baseline, hence a 3.

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 states the tool's action ('Match'), the inputs (text layers from extract-text-layers, a .docx table), and the output (translations.json). It differentiates itself from siblings by explicitly referencing the pipeline: it consumes output from extract-text-layers and produces input for apply-text-translations. This is a specific verb+resource+scope statement that leaves no ambiguity about the tool's role.

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 implies usage context by mentioning 'previously extracted with extract-text-layers' and 'ready for apply-text-translations', which positions it as an intermediate step. However, it does not explicitly state when to use this tool over alternatives or when not to use it (e.g., if translations already exist). There is no explicit exclusion or alternative routing, so it falls under implied usage rather than clear guidance.

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