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

While annotations declare readOnly/idempotent/safe properties, the description adds crucial behavioral context: status state machine (pending/processing/completed/failed), specific polling limits (20 min max), return field semantics, and cost ('Free'). No contradiction with annotations.

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?

Information-dense and well-structured with logical flow: purpose → returns → polling protocol → success path → error path → timeout handling → cost. Each sentence serves a distinct purpose, though the timeout instruction adds slight verbosity necessary for clarity.

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?

Comprehensive for a polling tool: enumerates return fields (compensating for lack of output schema), documents the complete lifecycle including timeout edge cases, and clarifies relationships to sibling tools (ceevee_generate_report, ceevee_download_report).

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 100% with report_id fully documented ('Report ID from ceevee_generate_report response'). Description references the parameter in usage examples but does not add semantic meaning beyond the schema, meeting the baseline for high-coverage schemas.

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 specific action ('Get report status and metadata') and explicitly distinguishes from siblings by noting it operates 'without PDF' and identifying itself as 'the polling tool for ceevee_generate_report'. Clearly defines return values (status, title, type, inputs, summary).

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?

Provides explicit polling protocol ('call every 30 seconds, up to 40 times'), names the exact sibling to use for next steps ('download PDF with ceevee_download_report'), and details error handling for both failure states ('relay error_message') and timeout scenarios ('stop and give the user the report_id').

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