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

With readOnlyHint=true annotation already declaring a safe read operation, the description adds valuable behavioral context: the returned image_id is ephemeral (valid 5 minutes), implying a time-bound processing model. It doesn't contradict annotations. It explains the lifecycle of the resource but doesn't disclose details like error behavior or rate limits, keeping it just below 5.

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?

Three sentences, zero waste. Each sentence earns its place: purpose+lifecycle, downstream targets, and a usage threshold. Front-loaded action and outcome.

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?

The tool has 3 params, an output schema, readOnly annotation, and a clear description covering purpose, lifecycle, downstream consumers, and parameter disambiguation. The 5-minute expiry is disclosed, which is a key operational detail. Minor gap: no mention of error handling for invalid uploads, but given the output schema and complete annotation coverage, this is adequately complete.

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%, so parameters are well documented in the schema. The description adds meaningful context: it clarifies image_base64 is specifically for 'locally uploaded files with no public URL' and notes 'No size limit here (unlike palette_extract's image_base64)', which is a genuinely useful differentiation that wouldn't be obvious from schema alone. This cross-tool comparison adds real value.

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 purpose: upload an image for ephemeral processing, returns an image_id valid for 5 minutes. It names the downstream tools (palette_extract or image_brief) that consume the output, and specifies a usage threshold ('any image over 50 KB'). It's specific with verb+resource+scope, though it doesn't explicitly distinguish from sibling ingest-like tools beyond naming consumers.

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 gives clear context on when to use this tool (for any image over 50 KB, as preprocessing for palette_extract or image_brief). It doesn't explicitly list alternatives or exclusions/when-not cases, which keeps it at 4 rather than 5, but the 50 KB threshold and downstream consumer names provide actionable guidance.

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