review_article

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

Annotations already declare readOnlyHint=false, destructiveHint=true, and idempotentHint=false, so the agent knows this is a non-idempotent write. The description adds that the recorded decision is the researcher's own for a single article, but says nothing about overwriting an existing decision or auth requirements — notable gaps given destructiveHint=true.

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?

A single well-formed sentence with no filler, front-loading the core action. Appropriately sized, though somewhat sparse for a four-parameter mutation tool.

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 no explanation, but for a write tool with four required parameters and 25% schema coverage the description leaves behavioral and parameter details thin. Adequate but with clear gaps.

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 25% (only run_id documented), so the description must compensate. It meaningfully maps 'include/exclude decision', 'reason', and 'one article' onto decision, reason, and uid, but leaves run_id's source and uid's identity unexplained — partial compensation only.

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: 'Record ... include/exclude decision and reason for one article.' The phrase 'the researcher's own' hints at differentiation from the bot_* and bulk-record siblings, but it never names an alternative, so the distinction remains implicit.

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?

No when-to-use guidance and no exclusions. With closely related siblings like record_screening_decisions, next_screening_batch, and add_skipped_articles, the description never tells the agent which path selects this tool, leaving it to inference.

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