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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is carried by structured data. The description adds value beyond that by enumerating the artifact types returned (grammar, fixture, sources, workflow) and framing the result as a downstream instruction, which tells the agent this is a self-contained briefing rather than a data query. It stops short of saying whether the fixture is inline text or a resolvable reference.

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?

Two sentences, front-loaded with what the agent receives and followed immediately by the next action. Nothing is redundant with the title or the empty schema, and every clause carries information.

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?

For a zero-parameter, read-only guide with an output schema available, the description covers both content and follow-on step, which is sufficient to invoke correctly. The only gap is the absence of any routing signal among the cluster of sibling *_guide tools.

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?

The tool takes zero parameters and the schema is an empty object, so there are no parameter semantics to document; baseline 4 applies. The description correctly implies no configuration is needed before use.

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?

The verb 'GET' plus an enumerated payload (reaction-model grammar, runnable synthetic fixture, research sources, experiment-to-replication workflow) makes clear exactly what this tool returns, which is more specific than a generic 'guide' label. It does not, however, distinguish itself from the many sibling guide tools (twin_benchmark_guide, beta_cell_guide, patient_model_guide, results_gap_guide), so an agent cannot tell from the text alone which guide applies.

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 'NEXT: run_twin_experiment with a declared model and perturbation arms' line gives an explicit sequencing instruction and even names the prerequisite inputs, which is genuinely actionable. What is missing is any exclusion or pointer for when to choose a different guide, and no prerequisites for calling this tool itself are stated (though the zero-parameter schema implies none).

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