Create tag

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

Annotations already declare readOnly=false, destructive=false, openWorld=true, and idempotent=false, so the safety profile is covered. The description adds genuine value by disclosing duplicate-name behavior (returns the existing tag rather than erroring), though that softly echoes idempotent semantics that the annotation denies. It does not state what object comes back on success or any auth/permission requirement.

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?

It is short and front-loads the action, but the raw "POST /api/v1/core/tags/create/" line and the restated title are low-value filler, and the Args block adds nothing for a one-parameter tool. The meaningful content (duplicate handling) is buried in a parenthetical.

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 one-parameter mutation with no output schema, the core facts an agent needs are largely present: it creates a tag, and duplicates return the existing record. Missing pieces are the shape of the response and any name-format constraints, which matter because the return value differs depending on whether the tag already existed.

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% for the single parameter, so the description must carry the load, but "name: Tag name" merely restates the property name. No constraints are given: case sensitivity, allowed characters, length limits, or whether uniqueness is enforced case-insensitively.

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?

"Create a tag" is a specific verb plus resource, and the parenthetical clarifies the duplicate-name case, so the agent knows this is the create path and not archivebox_get_tag or archivebox_rename_tag. It stops short of explicitly naming the sibling it replaces (e.g., get_tag/search_tags) for lookup-first workflows.

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?

Usage is implied by the verb: use it when a tag does not yet exist. The note that an existing tag is returned when the name is taken is a useful implicit hint that no pre-check is needed, but there is no explicit when-not guidance or reference to alternatives such as archivebox_get_tag or archivebox_search_tags.

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