Analyse a passage word by word

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, offline/closed-world), so the description's contribution is additive: it discloses that the dataset is bundled/offline, that all parses are returned rather than a single best reading, that glosses are not a translation, and that a CC BY-NC-SA 4.0 notice accompanies results. Missing detail on result size limits and continuation behavior is left to the schema.

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?

Densely front-loaded: the return contents come first, then the input convention, then the interpretive caveat. Every sentence carries information, though the license-notice sentence is marginal utility for tool selection.

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 5-parameter, read-only analysis tool with no output schema, the description covers what is returned, how to address the passage, and how to interpret results. Pagination across a segment is delegated to the schema's limit/offset descriptions, which is acceptable given 100% schema coverage.

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%, so the baseline is 3, and the description earns above baseline by clarifying that uid accepts 'any citation get_text accepts', giving segment format examples ('mn10/3' or its number), and framing paragraph as a VRI alternative to segment. It does not explain limit/offset continuation semantics in prose, which keeps it from a 5.

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 (word-by-word analysis of a passage from the bundled Pāli text) and enumerates exactly what each analysed word yields: compound/sandhi split, headword, grammar, root, short meaning. That level of return detail clearly separates it from siblings like get_text (raw text) and lookup_pali (single-word lookup).

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?

Establishes the workflow dependency by telling the agent to pass a citation plus a segment ref obtained from get_text, or a VRI paragraph instead, which is real routing guidance. It also warns that 'dictionary glosses are not a translation' and that every possible parse is listed, which is applicable use guidance. It stops short of naming an explicit alternative or when-not-to-use case, so 4 rather than 5.

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