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

Annotations already declare readOnlyHint=false, idempotentHint=false and destructiveHint=false; the description adds real value on top by giving the 5 MB limit and spelling out the practical consequence of non-idempotency ('repeated uploads create separate templates'). It does not say what happens on validation failure (bad placeholders, wrong PPTX aspect) or whether the upload is scoped to session/org.

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?

Front-loaded with the action and the hard limit, and every clause carries information (formats, placeholders, encoding, downstream id, non-idempotency). It is dense to the point of being a single semicolon-chained block, which costs some scannability.

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?

An output schema exists, so return values need not be explained, and the description still tells the agent the key return artifact (template id). For a 5-parameter mutation tool the coverage is nearly sufficient; the gaps are session/org scoping and error behavior.

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 only 40%, so the description must compensate and it partly does: it explains the accepted file formats per `kind` and that `data_base64` must be raw bytes, not a path. But `session_id` and `organization_id` get no treatment in the description, leaving two of five parameters explained only (or not at all) by the schema.

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?

Opens with a specific verb+resource ('Upload a template') and immediately constrains it by size and by the two supported kinds (report vs presentation). The downstream hook ('pass the returned template id to generate_research_output') makes its role in the workflow unmistakable and separates it from upload_research_source.

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?

It states what file types are acceptable per kind (Markdown/TXT/DOCX with placeholders; 16:9 PPTX theme/layout) and the size ceiling, which is clear 'when this applies' guidance. It also warns that repeated uploads create separate templates, steering the agent away from assuming replacement. It stops short of naming an explicit alternative or exclusion.

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