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

With no meaningful annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=false), the description carries the full burden. It discloses the upload flow: bytes go straight to storage, never read into conversation, URL is short-lived, reference is single-use, and no custom authorization is needed. These are key behavioral traits beyond what annotations convey, and there is no 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 tight, with every sentence earning its place. The core purpose is front-loaded, followed by a clear usage sequence, and ends with the alternative-tool routing. No filler, no redundancy. It reads naturally and is easy to scan.

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 two-step upload tool with no output schema, the description covers the entire workflow: what the tool returns, how to use it, and where to pass the reference. It also addresses authorization and the alternative for generated text. An agent has everything needed to call this tool correctly in context.

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 the baseline is 3. The description adds value by explaining that size is signed and any other length is rejected, and that directory parts are stripped from the name. This goes beyond the schema's basic descriptions, helping the agent understand constraints. It does not cover every edge case, so 4 is appropriate.

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 verb ('reserve an upload') and the resource (a file upload URL). It explicitly distinguishes from the sibling twprojects-create_file by specifying when to use each. The examples ('a PDF, an image, a signed document') ground the purpose, making it unambiguous.

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 explicit when-to-use (any file that already exists) and when-not-to-use ('Prefer twprojects-create_file only for short text you are generating yourself'). It names the alternative tool directly, and outlines the follow-up steps (send bytes, pass reference to other tools). No inference required.

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