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

Annotations already mark readOnlyHint=true and destructiveHint=false, so the read-only profile is covered; the description adds genuinely useful behavior beyond that: it explicitly states it does not inspect a birth chart, and that it returns only id and name for a dictionary look. A minor gap: it does not note whether the full 301 entries are returned in a single response or paginated, but the scale is in the description and the compact parameter in the schema covers the size concern.

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?

Three sentences: purpose/resource, core disambiguation (dictionary vs detection), and routing to the two relevant sibling endpoints. Every sentence earns its place, with the most important behavioral distinction ('does not inspect a birth chart') positioned immediately after the purpose, and no repetition of the schema or title content.

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 simple GET with 0 required params, no nested objects, and no output schema, the description covers everything an agent needs to decide and call it: the catalog scope (301 entries), the returned fields (id, name), the non-behavior (no chart inspection), alternatives for detail-reference and detection, and the intended use cases. Parameter semantics are fully delegated to the rich schema descriptions, and the service profile is covered by annotations.

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 fully documents lang (enum values, default, English fallback behavior), family (enum plus the quirk that 'classical' matches nothing), and compact (columnar shape with token savings). The description itself adds only marginal value here, but the not-in-repet coverage keeps this at the baseline of 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 opens with a specific verb and resource: 'Browse the 301-entry Vedic planetary-yoga glossary' and states exactly what is returned: 'id and name for every cataloged yoga.' It explicitly disambiguates itself from the sibling tools by clarifying this is a dictionary listing, not a chart-driven detection, and the 'Use GET /yoga/{id}' sentence separates it from get_vedic_astrology_yoga_id and post_vedic_astrology_yoga_detect.

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 states for an explicit mental model: 'This is a dictionary lookup, not chart-driven detection: it does not inspect a birth chart,' and then lists concrete alternatives with the condition for each: 'Use GET /yoga/{id} for the full glossary entry, or POST /yoga/detect to run all 48 detection rules against a specific kundli.' It also gives the target scenario 'yoga-browser UIs, search, and progressive data loading,' so an agent knows when to pick this over the compute-centric POST siblings.

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