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

Annotations carry the safety profile (destructiveHint=false, openWorldHint=true), and the description usefully adds the UTC-today default and the hard error on unresolved places. However, readOnlyHint=false is left unexplained by a description that reads as a pure computation, so an agent gets no signal about what side effects or external lookups occur.

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 front-loaded sentences, each carrying real information (output content, defaults, input modes, error behavior). The enumeration of return fields is slightly redundant given an output schema exists, but nothing is wasted.

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?

Given an output schema exists, the description covers the essentials an agent needs: date default and format, timezone expectation, birth-data input modes, and failure behavior. Gaps are the unexplained language/location_timezone parameters and the noon-at-which-location convention used for transit computation.

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?

Top-level schema coverage is reported at 0%, and the description compensates for the important ones: date format YYYY-MM-DD, IANA timezone, and birth accepting a place name or verified coordinates. The 'language' and 'location_timezone' parameters are never mentioned, so two of four top-level params remain semantically opaque.

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?

States a specific verb and resource: 'Return gochar transits at local noon for a date ... mapped to natal houses from the Ascendant and Moon.' The natal-chart mapping plus graha drishti/retrograde output clearly separates it from sky-only siblings such as get_sky_now or compute_chart.

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?

Usage context is implied by the required 'birth' payload, so an agent can infer this is the personalized timing tool, and the error-on-unresolved-place rule helps. But it never explicitly says when to prefer this over get_sky_now, get_my_timing, or find_auspicious_time, nor whether birth profile storage is a prerequisite.

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