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

Annotations already flag write/destructive, but the description adds substantial beyond-schema detail: replacements apply in order and are all-or-nothing, find must match exactly once unless `all`, regex mode is DOTALL with \1 backrefs, failures change nothing and report which replacement failed, and changes breaking Jinja syntax are refused. It also notes dry_run previews and the old template is retained in history, so the destructiveness is bounded and recoverable.

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 purpose and the sibling comparison are front-loaded, and each following paragraph covers a distinct concern (identifiers, replacement semantics, validation/safety). It is dense and long for a tool description, with a couple of clauses that could be tightened, but no sentence is filler.

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 5-parameter mutation tool with no output schema and an open-world, destructive profile, the description covers identifiers, replacement format and matching rules, failure semantics, dry-run preview, rollback via history, and safe-call guidance. Nothing an agent needs before calling it is missing.

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 description coverage is 0%, so the description carries the full burden and does: seliee_template_key is the slot (prefix optional), replacements is a max-20 list of {find, replace, all?, regex?}, dry_run previews without saving, and template_id/template_uuid are alternative identifiers. It also clarifies that seliee_template_key and replacements are required despite a schema showing zero required 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?

Opens with a specific verb and scope: change a few exact pieces of text inside ONE slot of a template, leaving the rest untouched. It immediately distinguishes itself from edit_template_key by scope of the change, so an agent can pick between them without reading either 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?

Explicitly names the alternative (edit_template_key) and the condition that selects it: use this when only part of a slot changes, since the sibling resends the whole slot. It also points to get_template_key as the source of the exact text to copy, covering the prerequisite step.

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