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

Annotations only cover readOnlyHint and openWorldHint, so the description carries the real disclosure burden and does well: it says citations may be written any way a person writes them, that `language` is a preference and not a filter (results report their actual language), and that each reply includes five verses either side with translations. It stops short of describing error behaviour for an unresolved citation or the exact shape/ordering of the returned payload.

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?

Front-loaded with what you get, then when to call it, then the alternatives, then the traversal recipe — a sensible information order with no filler sentences. It runs three paragraphs and the final traversal paragraph is dense, but every clause is actionable rather than decorative.

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, the description must describe the return payload, and it does: the fields returned, the word-by-word table's purpose, and the neighbour verses included under `context`. Combined with the routing guidance and citation flexibility, an agent has everything needed to call this correctly.

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; the description earns above that by adding semantics the schema doesn't: the `verse` parameter accepts human-written citations, not just internal ids, and `context` is the hook for the chained traversal recipe using the neighbour's `unit_id`. The `context` 0–5 bound and language enum remain schema-only, which is fine.

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?

Opens with a specific verb and resource ("Fetch one verse whole") and enumerates exactly what comes back: Devanāgarī, IAST, word-by-word breakdown, translation, commentary, optional neighbours. It explicitly distinguishes itself from search_texts (discovery) and browse_work (sequential reading), so an agent can route between the three without opening a schema.

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?

States concrete triggers ("after search_texts when you are going to quote", "whenever the user names a verse") and names the alternative for the other case (browse_work for a chapter or whole book). It even documents a pagination recipe: re-call with context 5, then the unit_id of the last neighbour marked "after".

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