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

With no annotations, the description carries the full burden: it establishes this is a read of previously cached material by other agents and discloses the shape of the content returned, which is genuinely useful. It does not state whether results are paginated beyond the schema's limit, nor any ordering/freshness behavior beyond 'cached'.

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?

Four sentences, front-loaded with the core action and ending on a genuinely non-obvious interpretive heuristic. No filler, though the filter sentence slightly duplicates schema 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?

No output schema and no annotations, so the description must stand alone — it covers content categories, filters, and a usage heuristic. It stops short of return shape/ordering details, but is otherwise adequate for a zero-required-param read tool.

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 description coverage is 100%, so the baseline is 3. The description restates the filter fields and clarifies piece_id means a node appearing as from or to, but adds little beyond what the schema already documents.

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 gives a specific verb+resource (read cached crossings) and names what the resource contains (productive insights, dead-end markings, live-wire open questions), which clarifies the domain term. It implicitly separates itself from the write-side sibling save_crossing, but does not explicitly distinguish itself from nearby read tools like get_connections or trace_field.

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?

Filter dimensions are listed, implying how to narrow results, and the closing heuristic ('dead-end records are often more useful') gives real guidance on interpretation. However there is no explicit statement of when to reach for this tool versus sibling reads, nor any exclusion criteria.

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