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

Annotations already declare readOnlyHint=false, idempotentHint=true and destructiveHint=false, so the description is not carrying the safety burden. It adds meaningful context by disclosing the replace/overwrite semantics implied by an upsert, but says nothing about which key drives replacement or whether an existing template is silently overwritten or errors out.

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?

Two short sentences, zero waste, with the core action front-loaded and the syntax rule immediately after. Nothing needs trimming and nothing is buried.

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 six-parameter upsert with a nested data object and no output schema, the description covers the action and the placeholder syntax but leaves open what identifies the target template for replacement, how `data` values relate to body substitution at render time, and what the caller gets back. Annotations and rich schema descriptions cover much of the gap, so it is adequate rather than 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 the schema already documents all six parameters and the baseline would be 3. The description adds information the schema does not: a mini-language for the body with {{field}} placeholders and {{field|default}} fallbacks, which is real semantic value beyond "Body, with {{fields}}".

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 with upsert semantics ("Create or replace a template"), which inherently separates it from delete_template, get_template and list_templates. It stops short of naming any sibling explicitly, but the operation is unmistakable.

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 second sentence explains placeholder syntax, which is how to fill the body rather than when to call this tool. There is no guidance on when to prefer this over get_template/list_templates, no statement of prerequisites or permissions, and no note on what happens if the name already exists.

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