gitflic_user_projects

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

The annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered elsewhere. Beyond restating the purpose, the description adds nothing: it does not mention pagination or the `limit` behaviour, the token-slimming default that `raw` disables, or the fact that idempotentHint=false means repeated calls may return different result sets.

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?

A single short sentence is maximally concise and front-loaded with the verb. It is concise at the cost of under-specification rather than because the content is tight: the sentence is too small for eight parameters and the default-slim response behaviour.

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?

With eight parameters, one required, no output schema and a non-trivial slim-versus-raw response mode, the description should do more than a five-word purpose statement. It leaves the required `alias` parameter, the default response narrowing, and the interaction between `q`, `sort` and `fields` entirely to the schema.

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 88% and every documented parameter already explains itself, so the baseline of 3 applies. The description adds no meaning on top of the schema and does not explain the one undocumented parameter (`alias`, the required one), nor does it resolve the "public" wording against the `private` filter.

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?

The description names a specific verb and resource ("List public projects of a user"), which is enough to separate it from gitflic_user_followers or gitflic_user_get. However, the qualifier "public" conflicts with the schema's `private` flag, which lets the caller fetch only private projects too, so the stated scope is narrower than the tool's actual behaviour and no sibling is named as an alternative.

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?

There is no when-to-use guidance, no prerequisite such as authentication or alias resolution, and no pointer to alternatives such as gitflic_user_search or gitflic_user_get. The agent must infer that this tool is for enumerating a user's owned projects rather than for searching, and must infer that from the name alone.

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