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

Annotations already carry the behavior profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false, openWorldHint=true), so the bar is lower. The description adds cost context ('10 credits (Tier 1)') and how inputs vary, but says nothing about generation latency, what resource is produced, or auth needs. It is accurate and non-contradictory but adds only modest behavioral detail.

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 dispatch purpose, then the type enum, then the required-field rules; every sentence carries signal. The full report_type enum is duplicated from the schema and the bracketed metadata lines add some clutter, keeping it just short of maximally tight.

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 existing output schema (returns need no explanation) and annotations covering the safety profile, the description is complete on the core dispatch mechanism and the per-type input requirements, which is what an agent needs to invoke it. It leaves the numerous optional parameters (depth/extended pricing, whitelabel, language, fields, precision) to the schema, which is acceptable but not exhaustive for a 14-parameter 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 only 43%, so the description must compensate, and it does so for the critical part: the JSON schema marks only report_type as required, whereas the description supplies the conditional requirements (chart for most types, chart1+chart2 for synastry, seed with optional chart for tarot). This is genuine information the schema cannot express, though it does not describe the optional controls (depth, whitelabel, language, precision).

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 ('Generate Report'), declares the scope ('Single endpoint over the 12 type-specific renderers'), and enumerates all 12 report_type values. This lets an agent immediately distinguish it from the per-type sibling tools (astroway_reports_natal, astroway_reports_synastry, etc.) as the unified dispatcher.

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?

Clearly frames the dispatch model ('pass report_type plus the renderer-specific inputs', 'one method instead of 12') and gives the required inputs per type (chart for most, chart1+chart2 for synastry, seed for tarot). It stops short of explicitly naming when to prefer this over an individual per-type renderer endpoint or stating exclusions, so it is context-rich but not fully prescriptive.

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