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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false. The description goes far beyond these by detailing exact HTTP methods, endpoints, response contents (palette, 64 indices, row format, source values, kind metadata), state distinctions (Undrawn, Refused, Blank, In progress, Complete), and error conditions (404 for missing/withdrawn/moderation-hidden). It also explains the immutable one-year marker and the thumb image behavior. This adds substantial behavioral context the annotations cannot convey.

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 long but front-loaded with the core purpose in the first sentence. Every subsequent sentence adds unique operational details (endpoint, thumb, response format, sources, fallback instructions). There is minimal redundancy; each piece is essential for correct invocation and interpretation. It is not concise in word count, but it is appropriately dense for a tool with many edge cases.

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?

Despite having only 2 parameters and no output schema, the description is remarkably complete. It specifies the exact JSON structure expectations (palette, indices, rows), the source enumeration, kind-specific fields, error status for various states, the companion thumb endpoint, and even a fallback URL if the client can't use tools. An agent has all information needed to call the tool and interpret the response correctly.

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 0%, so the description must compensate. It does by explaining the meaning of 'type' (place, resident, kind, thing) and 'id' as the identifier in the URL, as well as mapping them to the tool's purpose. It also mentions response fields like 'source' and 'kind id' that relate to the type parameter. However, it doesn't explicitly describe constraints or intended values beyond the enum, but the endpoint structure and purpose make the semantics reasonably clear.

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's function: 'Deliberately read one current public place, resident, kind, or thing drawing.' This is a specific verb (read) and resource (drawing) with a precise scope (public, current). It differentiates from sibling tools by noting that ordinary map/place/window/census reads do not carry this payload, and by referencing the full catalog and front_door tool, making its unique role 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?

The description provides explicit guidance on when to use this tool: it points out that ordinary reads do not carry the drawing payload, suggesting this tool is necessary for drawing-specific data. It also mentions the companion image endpoint and the front_door tool for orientation. However, it doesn't explicitly name alternatives like drawing_history or draw_self, though the sibling list is visible. It gives clear context but stops short of a direct 'use this instead of X' comparison.

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