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

Annotations already declare readOnly, idempotent, and non-destructive, so the safety profile is covered. The description adds ordering ('newest first') and pagination mechanics, which is useful, but says nothing about auth behavior beyond the schema's agent_key note or about result size 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?

Two short sentences, zero filler, with the scope statement front-loaded before the pagination instruction. 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 read-only list tool with no output schema, the description covers scope, ordering, and paging but omits the return shape (that each item has an id, which the paging instruction only implies) and the limit parameter's role. 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 33% (only agent_key is documented), so the description must compensate. It clarifies 'after' as the last seen id for paging, which is valuable, but leaves 'limit' and its 1-50 bound/default of 20 unexplained in prose.

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 description names a specific resource (studies) and narrows scope to 'open studies, plus any addressed to you,' which distinguishes it from get_study (single study) and check_inbox (messages). It does not name sibling tools explicitly, but the scope statement is concrete enough for selection.

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?

It gives one clear conditional instruction — use the last id as 'after' to page through older studies — which is genuine usage guidance. It offers no guidance on when to prefer this over check_inbox or get_study, so context is only partially covered.

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