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

Annotations already establish the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false, openWorldHint=false), so the description only needs to add context. It usefully discloses that output is one line at a time and aimed at voice, but omits how many cards exist, whether n is bounded, or what 'defaults to today's reading' implies when no reading exists.

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 opens by duplicating the title verbatim ('Gita Scroller. Today's reading one line at a time, for voice..'), including a doubled period, then appends a catch-all feature list that relates to sibling tools rather than this one. It is not front-loaded around what a caller does with this specific tool.

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 paged read tool with three optional parameters and no output schema, the agent still lacks the essentials: how many cards a reading contains, whether to advance n sequentially, and how this differs from gita_get_today. Annotations cover safety, but the call-shape gaps are real.

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 description coverage is 100%, so the schema already documents n, date, and reading with defaults. The description adds the notion of 'one line at a time' that maps loosely to n, but contributes no additional format or constraint detail. Baseline 3 is correct when the schema carries the parameter burden.

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 identifies the resource (today's Bhagavad Gita reading) and the paging granularity ('one line at a time'), which is more specific than a bare name restatement. However, the second sentence is a generic app-level blurb covering many sibling tools ('daily verses, plans, search and verse lookup; whole books from the Library'), so it does not clearly distinguish gita_get_card from gita_get_today, gita_get_reading, or gita_get_chapter.

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?

It hints at a context ('for voice') but never states when to use this tool versus gita_get_today, gita_get_verse, or gita_get_reading. There is no guidance on how to paginate through cards or how to know when the sequence ends, which is exactly what an agent needs for a paged tool.

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