scan_mailbox

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

The description adds useful behavioral traits (checkpointing, resumption, new mail only after full scan), but it contradicts annotations: readOnlyHint=true while description says it persists data to local database. Per rules, score 1 for contradiction.

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 description is well-structured in three paragraphs: purpose, internal behavior, parameter guidance. Each sentence adds value, no fluff. Front-loaded with key action.

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?

Given 3 params and no output schema, the description covers purpose, internal mechanics, parameter usage, and default behavior. It lacks error handling or prerequisites but is largely complete. The contradiction slightly detracts.

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 coverage is 0%, so description carries burden. It explains 'folders' allows specific folder selection, 'max_messages' caps the run, and 'account' is required. This adds meaning beyond the schema's basic types and defaults.

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 clearly states the tool scans Yahoo account folders, pulling header-level data only. It specifies the resource (Yahoo account folders), action (scan), and scope (header-level). This distinguishes it from sibling tools like get_message_headers or triage_new_mail.

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 description provides when to use (default scans all except Trash/Drafts/Sent, can limit folders or max_messages) and mentions checkpointing for resumption. However, it does not explicitly compare to similar tools like start_scan_job or get_scan_status, leaving some ambiguity.

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