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

Annotations already disclose the safety profile (readOnlyHint=false, non-idempotent, openWorldHint=true), so the bar is lower. The description adds value with the cost warning (5,000 credits, ~50% of free monthly budget, confirm first) and the format-suffix behavior, but says nothing about what the output is returned as (URL? binary?) or auth requirements, and the visible text is cut off mid-explanation.

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?

Purpose is front-loaded in the first clause, which is good. However the prose is verbose and appears truncated, suggesting it runs long without a clean structure or summary of the key call-shape decisions. It is not padded with pure tautology, but it could be tighter.

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?

An output schema exists, so return-value explanation is not required. The description covers the document's content intent and its relationship to the vedic gemstones endpoint, plus cost. But with 7 parameters, 43% schema coverage, and a truncated description, an agent is left without guidance on several inputs and on how the produced PDF/HTML is delivered.

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 43%, so the description would ideally compensate for the undocumented parameters. It only adds the `?format=html` toggle beyond the schema; the rich nested `chart` object, `school`, `language`, `precision`, `whitelabel` and `wearingFrom` receive no extra narrative. The (truncated) remainder may have covered more, but on the evidence shown the description adds marginal parameter value.

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 gives a specific verb+resource: producing a 'ratna prescription' (gemstone report) as a multi-page A4 PDF by default or live HTML via `?format=html`. That is concrete enough to distinguish it from generic report siblings like astroway_reports_vedic_kundli, though it never explicitly contrasts itself with the closest siblings. The text is truncated mid-sentence, so full purpose is not verifiable.

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 the report shares astrology with `POST /vedic/gemstones` and adds document-only content, which implies when this is preferable (you want a formatted document, not a data table). It does not name an explicit alternative tool in the sibling set or say when NOT to use it. The credit warning ('confirm with user before invoking') is present but is cost guidance rather than usage routing.

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