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

With no annotations, the description carries the load and does well: it discloses the cost/auth profile ('FREE, no key'), the 31-day date window, the default of yesterday, and the shape of the return (grouped counts plus example names/numbers). It also notes alternate output channels (JSON endpoint, ?format=text). It does not cover failure behavior for out-of-range dates, keeping it at 4.

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?

Everything is packed into one front-loaded paragraph that opens with the value proposition ('FREE, no key') and the data content. The trailing endpoint/format note ('Also GET /daily/new-companies ...') is somewhat implementation-flavored noise for an agent invoking an MCP tool, slightly diluting density.

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 no output schema and no annotations, the description steps in to describe the return shape (grouped by SIC section/sector, with counts and example companies) and the data source (Companies House). An agent has enough to call it correctly; only edge-case behavior and sibling routing are missing.

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 baseline is 3, but the description adds genuinely new meaning: the date parameter is constrained to the last 31 days, which the schema does not state. The 'examples' parameter is only echoed (3 default, max 5) from the schema, so it adds no new information there.

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: 'yesterday's new Companies House incorporations, grouped by SIC 2007 section/sector with counts and example company names and numbers'. An agent immediately knows what it returns. It does not distinguish itself from close siblings like new_cos_discover or new_cos_pack, so it stops short of a 5.

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?

Usage context is implied: 'Daily data drop', 'Optional date (YYYY-MM-DD, last 31 days)' tells the agent the window of applicability. However, there is no explicit when-to-use-vs-sibling guidance despite four related tools in the family, and no statement of when this tool is inappropriate.

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