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

Annotations already establish read-only, idempotent, non-destructive behavior, and the description adds genuinely new context: ubi_synthetic is fabricated demo data, results should report sample denominators and exclusions, and public-study scope excludes private cohorts. That is meaningful analytical caveat beyond what annotations carry, though nothing is said about result size or 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?

Front-loaded with the operation, then mode list, then caveats, then an example – a sensible ordering with no filler. The mode list is crammed into the opening sentence and would read better as a short enumerated line, 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?

An output schema exists, so return values need not be described, and the annotations cover safety. The description supplies the essential missing pieces – how to discover study IDs, the synthetic-data caveat, and the reporting discipline for denominators/exclusions. Only the mode-selection guidance and per-mode prerequisites remain unaddressed.

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 oneOf discriminator already documents all seven analysis variants and their fields, so the schema does the heavy lifting. The example payload {'analysis':'gene_profile','study':'ubi_synthetic','gene':'TP53'} illustrates the calling shape but adds no per-parameter meaning beyond the schema.

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?

Opens with a specific verb+resource ("Analyze an installed public cancer genomics study") and immediately enumerates the seven analysis modes, so an agent knows both the shape and the scope of the operation. It also distinguishes itself from siblings by naming get_capabilities as the listing tool and the Ubi platform as the route for private data.

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?

Clear routing is given: use get_capabilities(source=study) to list installed studies, use the Ubi platform for private data. What's missing is guidance on choosing among the seven analyses (e.g. compare vs co_occurrence, or which survival endpoint), which the agent must infer from the mode names alone.

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