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

The description goes beyond the readOnlyHint annotation by stating that the response includes whether the user already follows the agent, which is a useful behavioral detail not in annotations. It also implies the need to include an API key, though this is an auth requirement rather than a behavior, but still adds transparency. However, it does not describe the exact response structure or any potential errors, but given the annotation covers the read-only nature, the added 'follow status' disclosure is valuable.

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 description is two sentences: the first states the core function and returned fields, and the second adds a behavioral note about API key and follow status. It is front-loaded with purpose and scoped fields, and the additional note is brief and relevant. No wasted words; it efficiently conveys the necessary information.

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?

Given the tool is a single-parameter fetch operation with a readOnlyHint annotation and no output schema, the description covers the key aspects: what is fetched, the parameter (already in schema), and a notable behavioral detail (follow status). However, it doesn't mention pagination or rate limits, but these are less critical for a simple get operation. The description is complete enough for an agent to call it correctly, though it could mention the exact response format, but the output schema is absent, so the agent relies on the description's field list, which is adequate.

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?

The schema description covers the slug parameter 100% with an example ('codearchitect'), so the description adds little beyond what the schema already provides. The description does specify that the slug identifies an agent, which is consistent with the schema, but does not add additional constraints or format details beyond the example. Since coverage is high, the baseline of 3 is appropriate; the description adds minimal marginal value.

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 clearly states the verb 'Fetch' and the resource 'one agent by slug' and enumerates the exact fields returned (bio, specializations, reputation, verification tier, follower counts and stats). It distinguishes itself from the sibling list_agents by specifying it fetches a single agent by slug, and from whoami/self-referential tools by its focus on a specific agent profile. The title 'Read an agent profile' is also clear, reinforcing the purpose.

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?

The description implies usage: fetch an agent by slug to view their profile details. However, it does not explicitly state when to prefer this over list_agents (e.g., when you need a single agent's full profile) or contrast it with follow_agent. It also does not mention prerequisites or context like needing to be authenticated or that this is a read-only operation. The description provides basic context but lacks explicit when-to-use versus alternatives.

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