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

Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=true, and destructiveHint=false, covering the safety profile. The description adds some behavioral texture with "line by line" and "read a passage at a time," suggesting output granularity/paging, but it never clarifies what is actually returned or how a plan differs from a reading. Baseline 3 is appropriate given the annotations carry the safety burden.

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 opening sentence is front-loaded and short, but the second sentence is a comma-spliced catalog of unrelated features (daily shabad, search, Ang lookup, whole books) that adds noise rather than signal. It is compact but not well-structured; the feature list does not earn its place.

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 single-parameter read-only getter with full schema coverage and safety annotations, little is strictly required. Still, the description never clarifies the return granularity (lines vs. passage) or how a plan id differs from a reading id, and it conflates sibling capabilities, leaving the agent slightly under-informed for a tool sitting in a dense sibling cluster.

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% and the schema already documents that id accepts a reading/plan id from list_readings or a plan name like "japji." The description's "one reading or plan" merely echoes this without adding format, casing, or lookup syntax beyond the schema. Baseline 3 when the schema does the heavy lifting.

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 core purpose is stated ("Scroll the Gurbani. One reading or plan, line by line"), which identifies the resource as a reading or plan retrieved linearly. However, the second sentence lists "daily shabad, plans, search, Ang and shabad lookup; whole books from the Library," which are actually the domains of sibling tools (gurbani_get_today, gurbani_get_ang, gurbani_get_shabad, gurbani_read_book, gurbani_search_readings). This conflation blurs rather than sharpens the boundary with siblings.

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?

There is no explicit when-to-use guidance and no naming of alternatives. With seven sibling gurbani_* tools (get_today, get_ang, get_shabad, read_book, search_readings, list_readings), the agent gets no signal about when this tool is the right choice versus those. "Read a passage at a time" hints at segment/pagination behavior but is not framed as usage guidance.

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