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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the bar is lower. The description still adds real context beyond them: the signals are proprietary, backtested over 10 years of NZX data, and flagged with 'validated alpha spreads', which honestly frames the score's provenance and limits.

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, followed by the component list and return shape. It is dense but each sentence carries information; the backtest sentence is slightly promotional yet relevant to interpreting the score.

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?

With an output schema present, return values need no elaboration, yet the description still summarises score, rating band, breakdown and active flags. For a one-parameter read tool with full annotation coverage, nothing an agent needs to invoke it correctly is missing.

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?

Only one parameter and schema coverage is 100%, with the schema itself giving format examples ("FPH", "AIR"). The description adds nothing about the ticker beyond 'NZX company', so the baseline 3 applies.

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?

Specific verb ('Get') plus a precisely scoped resource: a composite 0-100 alpha score for an NZX company, with the five constituent dimensions named. This clearly separates it from raw-factor siblings such as get_alpha_factors, get_factor_model and get_factor_grades, which surface individual signals rather than a single composite score.

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 description implies the use case (a single aggregate alpha read on an NZX company) but never states when to prefer it over get_alpha_factors, get_factor_grades or get_factor_validation, nor any exclusions or prerequisites. Usage is inferable but not guided.

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