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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered by structured data. The description still adds useful behavior: the content is procedural instructions to be followed, and a skill 'may name further files of its own' that must be fetched via the file parameter — a non-obvious read-recursion mechanic. It stops short of saying what the returned document looks like (format, size, whether it is truncated).

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 front-loaded with the core definition and the read-before-working rule, then branches into two clearly delimited bullets, and closes with the file-parameter note. The bullets are long and carry trigger-condition detail that borders on verbose, but every clause maps to a real routing decision rather than 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 two-parameter, read-only tool with no output schema, the description supplies what is needed: what a skill is, which one to read when, and the follow-up file fetch. The only remaining gap is the shape of the returned content (format and whether the skill body is paginated or truncated), which is minor given the low complexity.

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 100%, so the schema already documents both parameters and the baseline would be 3. The description goes beyond it by explaining what each enum value means in operational terms and by clarifying the file-parameter workflow ('read one by passing it as file'), which turns a generic 'a file the skill names' into an actionable instruction.

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 first sentence gives a concrete verb and resource ('Read one of Conciergr's skills') and immediately defines what a skill is ('step-by-step instructions for a bigger job, written by the team that builds Conciergr'). It then enumerates both enum values with a one-line description of each, so the agent can tell this apart from siblings like get_overview or get_assistant_knowledge without opening the 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?

It states an explicit precondition ('Before starting one of these jobs, read its skill and follow it') and gives concrete when-to-use triggers per skill, e.g. 'when the owner asks why the assistant keeps handing chats to the team' or 'when get_overview shows a document problem'. It even names the sibling that signals a need for tidy-documents, which is exactly the routing information an agent needs.

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