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

Annotations уже carry the read-only / non-destructive profile (readOnlyHint: true), so the burden is light, and the description adds real behavioral-semantic detail: the output contains a capped 0-100 score, five category scores, specific planetary pairs driving each category analysis, narratives, element balance, archeological classification, and 'most significant' aspects. This is genuine context beyond the annotations, though the sentence also takes credit for nothing destructive and never contradicts them.

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 is front-loaded — purpose in sentence one, output details in sentence two — and every item earns its place (score range, categories, pairs, narratives, element balance, archetype). It is a touch dense and slightly redundant in the structure, so not a 5, but there is zero filler.

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 the nested two-person inputs, four parameters, and no output schema, the description does a virtuous job spelling out the return contract: the score scale, the five categories, per-category planet pairs, narratives, element, archetype, and significant aspects. Minor voids (e.g., no explicit resolving of unknown birth times or the ordering of categories) are minor next to an otherwise rich output-shape description.

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%: person1/person2 nested objects, date, time, latitude, longitude, timezone, nodeType, lang, compact are each explained inside the schema. The description itself adds no parameter-specific guidance, which is acceptable under a full coverage baseline of 3; the only marginal addition is the implicit framing that the tool compares the two birth charts.

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?

Name leads with a specific verb and resource — 'Calculate a detailed compatibility score between two birth charts' — and states an explicit scope: overall 0-100 score plus five category hairdowns and several narrative components. The one gap is sibling differentiation: with the closely named post_astrology_synastry in the tree, the description never names it or says how this scoring tool differs from a raw synastry report, even though it leans on the word 'synastry' in its own scope sentence. That keeps it at 4 — clear but with an unexplored parenthetical difference.

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?

There is no guidance about when to pick this tool over alternatives: no exclusion, no conditional, and no mention of the obvious sibling post_astrology_synastry or post_astrology_composite_chart that would tempt an agent. The title's 'Compatibility Com' is weak evidence of usage intent, and the description never says what counts of siblings — e.g., 'for a quick scoring summary use this; for per-aspect data use synastry'.

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