save_project

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

With no annotations, the description carries the full burden. It does disclose one genuinely non-obvious mutation semantic: "Only the fields you pass are changed" (partial merge update), which is critical given that most fields default to empty strings. It does not state what happens on conflicting values, whether permission or auth constraints exist, or what the tool returns.

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 tight sentences with the upsert purpose front-loaded and no filler. The trailing country-format sentence reads as a dangling fragment appended to the paragraph rather than integrated, which slightly hurts structure.

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 an 8-parameter mutation tool with no annotations and no output schema, the definition covers the core upsert behavior and country format but leaves the primary key (site: domain? full URL?) and several fields unexplained. An agent could invoke it, but would be guessing on site formatting and array handling for keywords/competitors.

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% across 8 parameters, so the description must compensate. It only partially does: the country parameter gets a format explanation with examples ("India", "IN", "UK"), and the fields niche/location/country/keywords/competitors are enumerated as stored attributes. Format and expectations for site, notes, and business_name (5 of 8 uncovered) remain undocumented.

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+resource ("Save (or update) a site") and adds scope ("your own or a client's"), so the agent knows it's an upsert on a project/site record. Sibling tools like list_projects and scan_site are not named, so differentiation is inferable rather than stated.

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?

"Save (or update)" implies the create-or-modify case and the phrase "so every other tool knows its niche..." hints that this should be called before downstream tools. However, there is no explicit when-not guidance, no prerequisites, and no reference to an alternative tool for reading or deleting projects.

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