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

Annotations declare readOnlyHint=true, and the description is consistent with that ('Stateless: nothing is stored on Close Knit'), resolving the apparent tension of a 'build' tool being read-only. It adds real behavioral context — the output is a de-duplication state file path plus a scheduled-task prompt reporting only new listings — though it doesn't cover rate limits, auth, or error behavior.

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?

Purpose is front-loaded in the opening clause, and the second sentence adds the important stateless fact. The first sentence is a dense run-on list of artifacts that could be broken up, but there is little wasted content.

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 moderately complex tool with an output schema present, the description conveys what gets produced and that nothing is persisted server-side. Input-to-output mapping is thin, but the presence of an output schema covers return values, making the description largely sufficient for correct invocation.

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 57%, and the description mostly describes outputs (state file, prompt, per-district searches) rather than clarifying the inputs. It weakly maps 'filters' to must_haves/min_bedrooms/max_price and hints at area scope, but adds no concrete meaning beyond the schema, and 'postcode district' is loosely aligned with the finer-grained 'LSOA ids' parameter.

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 transformation ('Turn a finished search into a watch') and enumerates the artifacts produced (portal searches, filters, state file path, scheduled-task prompt). It is clearly distinguishable from the read-only query siblings, which makes a solid 4, though it never names an alternative explicitly.

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 phrase 'Turn a finished search into a watch' sets a clear precondition (a completed search) for when this tool applies. It gives clear context but offers no explicit when-not conditions or references to sibling tools, so it stops short of a 5.

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