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

Annotations already declare a safe, idempotent read, and the description adds real behavior beyond them: unread query strings are refused, dates after today or impossible dates are not pages, and pages over 48,000 characters are truncated at a line with a note naming the tool that returns the rest. These are exactly the error and limit conditions an agent needs before calling.

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 first clause is well front-loaded, and the catalog largely earns its space for a path-addressed tool. However, it is delivered as one enormous run-on sentence with a long comma-separated list of static site pages, which is hard to scan and could be grouped or trimmed.

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 one-parameter read tool with no output schema, the description covers what is returned (markdown), which paths are valid, how invalid dates and queries fail, and how truncation is signaled and where to go for the remainder. Only minor gaps remain, such as whether the markdown includes metadata headers.

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 would be 3, but the description goes well past the schema's single example by enumerating the distinct path grammars (fact pages, diff pages with from/to, year-scoped timelines, day/brief/trends pages) and their query parameters. This meaningfully expands what the single `id` string can be.

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 and resource — fetching a page's markdown twin by its path — and immediately makes the addressable surface concrete by enumerating path forms. An agent can distinguish this from siblings like entity_diff, entity_state, or search because those return structured answers while this returns a rendered markdown page at a path.

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 path catalog functions as strong context: it tells the agent which page types exist and how to reach them, and it cross-references entity_state's fact_pages for discovering fact pages. It stops short of explicit routing statements such as when to prefer fetch over entity_diff or search, so usage is well-scoped but not fully adjudicated against alternatives.

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