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

Annotations only cover the safety profile (readOnly, idempotent, non-open-world); the description adds substantive behavior: partial/non-exhaustive coverage, graph_status as an internal eligibility label rather than clinical validation, pathway_tags as raw unvalidated metadata, up to 3 PubMed IDs per row, and how unresolved inputs surface via status. This is exactly the extra context annotations cannot carry.

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 core purpose is front-loaded, but the rest is one long semicolon-chained paragraph mixing caveats, field semantics and error handling. Most sentences carry real information, yet the density and run-on structure make it harder to scan than it needs to be.

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?

There is no output schema, so the description must describe returns — and it does: intervention_type taxonomy, direction, pmids with URL template reference, graph_status, pathway_tags, and the status/next_step failure path. An agent has what it needs to call and interpret results.

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%, so the baseline is 3. The description adds only a little beyond the schema: it confirms the biomarker may be an Aviado id (schema says name/abbreviation/LOINC) and repeats that direction is optional, without new syntax or format rules.

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+resource with scope: 'All mixed interventions in Aviado's evidence graph that move a biomarker'. The word 'mixed' plus the note that non-supplement rows are context implicitly separates it from get_supplements_for_biomarker, but no sibling is named outright, so differentiation is inferred rather than explicit.

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?

Gives usable operating conditions: optional direction filter for up/down, 'check status first' with needs_confirmation/no_match meaning and next_step, and a warning that absence is not evidence of no effect. It stops short of explicitly telling the agent when to prefer this over get_supplements_for_biomarker or get_biomarkers_for_supplement.

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