register_project_file

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

Annotations already declare readOnlyHint=false and destructiveHint=false; the description adds the genuinely useful context they don't carry — the two-step prerequisite (a prior 201 from step 1) and the exact return payload {file_id, name} with a note that file_id is stable and reusable. It omits duplicate-registration behavior, which matters given idempotentHint=false.

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, front-loaded with the sequencing frame, then inputs, then the return contract. No filler; the example parenthetical for `name` earns its place. Slightly dense but well ordered.

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 mutating 5-parameter tool with zero schema descriptions and no output schema, the description covers the essentials: prerequisite step, key inputs, and return shape. The residual gap is the two optional metadata parameters (byte_size, content_type) and what happens on a second registration of the same s3_key.

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 the description must carry semantics. It meaningfully documents the two non-obvious parameters — s3_key as coming from step 1 and name as human-readable with a concrete example — but project_id, byte_size, and content_type go entirely unexplained in both schema and description.

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 a specific verb and resource ('record a file already POSTed') and pins its role as 'Step 2 of the upload', which distinguishes it cleanly from upload_file_to_project (step 1) and get_project_file (retrieval). An agent can place it in the workflow without opening any schema.

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 precondition is explicit: only call this after upload_file_to_project returned a 201 with an uploadUrl, and pass the s3_key from that step. It also names get_project_file as the downstream consumer. It stops short of stating what to do on re-registration or failure, so not a full when/when-not rubric.

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