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

With no annotations, the description carries the full behavioral burden. It discloses the error case (returns isError with {error:'not_found'} when slug is invalid or agency opted out) and notes that cultural-fit and cases are read-only (Knowledge-OS canonical). This provides useful behavioral context beyond the simple 'fetch' action, though it stops short of describing success response structure in detail.

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 sentences, front-loaded with the primary purpose and key source of input, followed by the error behavior and read-only note. No extraneous words; every sentence earns its place. This is a model of brevity.

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 there is no output schema, the description sufficiently communicates the expected content (specialisms, cultural-fit axes, up to 3 cases) and error behavior. It does not explicitly state the shape of the success response (e.g., an object with those fields), but for a single-parameter read operation this is a reasonable level of completeness. Slightly more detail on the return structure would push it to a 5.

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 already describes the single parameter (slug) with its source and constraints (100% coverage). The description adds no novel information about the slug itself beyond repeating the source of the slug. Since the schema does the heavy lifting, a baseline score of 3 is appropriate; the description's mention of what the profile includes is relevant to output, not the parameter's meaning.

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 action ('Fetch the full public profile') and the resource ('one marketing agency by slug'), and it distinguishes itself from siblings by specifying the source of the slug (from search_agencies or find_agency). This makes it unambiguous which tool to use when a slug is already known.

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 the appropriate usage: obtain a slug via search_agencies or find_agency, then call this tool to get the full profile. It does not explicitly state when not to use it or mention alternatives like submit_rfq, but the context is sufficient for an agent to understand the intended workflow. A clear 'use this after you have a slug' signal would be stronger.

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