save_profile

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

With no annotations, the description carries the full load and does well: it discloses merge semantics ('only the given fields change'), that scale/offset calibration applies to every job, that mirroring keeps proofs readable (sublimation use case), that cost fields make proofs include a cost estimate, and that open_driver_dialog captures vendor-only options into the profile. It omits persistence/overwrite risk for existing profile names and what happens when printer is omitted.

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 core statement is front-loaded in one sentence, followed by a compact, scannable parameter reference where nearly every line adds distinct information. Some lines are terse to the point of being cryptic (paper/tray phrasing) and the list lacks grouping, but there is little outright waste.

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 23-parameter mutation tool with no annotations, no output schema, and zero schema descriptions, the description is unusually complete, covering most parameters with values and side effects. It is still missing the required name's role, which printer the profile binds to, and make_default, so an agent can call it but not with full confidence on identity-binding fields.

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% across 23 parameters, so the description must compensate and largely does: it supplies accepted enum values (quality, color, duplex, intent, paper), numeric ranges for scale and offset, the default for dpi, and the formula behind ink_price_5pct. Gaps remain for the required 'name', 'printer', and 'make_default', which are not explained at all.

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 pair and resource ('Create or update a remembered print profile') plus the important upsert nuance that 'only the given fields change', which tells an agent this is a partial-merge write rather than a replace. It is clearly distinct from list/delete/set_default siblings by name and effect, though it never explicitly routes away from them.

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 context is implied rather than stated: the tags/notes line ('so it can be found later') and the tray/media note ('code from describe_printer') give indirect routing to describe_printer, but there is no explicit when-to-use/when-not guidance, no mention of set_default_profile versus the make_default parameter, and no prerequisites.

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