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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful non-schema context: the endpoint path, the two required chart inputs, and the 50-credit Tier 3 cost, which matters for a paid call. No auth or rate-limit detail, but nothing misleading.

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?

Front-loaded with the differentiator in the first sentence and the computation in the second; the bracketed metadata block is terse and each token (endpoint, required, cost) carries information. Slightly redundant with the schema on 'Required: chart1, chart2', but no wasted prose.

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 values need not be described, and the description covers what is computed, the required inputs and the cost. Given the crowded compatibility sibling set, the one gap is guidance on when this beats compatibility_full; otherwise it is complete for a read-only, idempotent computation tool.

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% and the nested chart object is thoroughly documented in the schema itself (date/time formats, timezone semantics, houseSystem letters). The description only restates the two required parameter names, adding no syntax or format meaning beyond structured fields. Baseline 3 is correct.

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 computation ('counts benefic/malefic planets in each partner's 7H from Lagna') and the exact output vocabulary ({beneficial|challenging|neutral}). The closing line 'NOT a numerical match score' actively separates it from the several score-based compatibility siblings (ashtakoot, dashakoota). An agent can tell what this returns without opening the schema.

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?

The negative disambiguation ('NOT a numerical match score') gives implied usage — pick this for qualitative 7H placement rather than point totals — but no alternative is named. With five compatibility siblings (ashtakoot, dashakoota, full, mangal_match, manglik_check) an explicit 'use X when Y' would be needed for a 4 or 5. Guidance is inferable, not stated.

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