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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered; the description earns its keep by disclosing the return shape (markdown sections) and a non-obvious behavioral rule — the snippet writes Parquet or keeps data in memory when provider terms limit storage. It stops short of saying what happens for an unknown slug (empty result vs. error).

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?

Front-loaded with the verb and return artifact, and the fallback behavior is placed last as a secondary instruction. The first sentence is a long enumerated clause list, but each item corresponds to real returned content, so little is wasted.

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 single optional-parameter read tool with no output schema, the description carries the return-value burden well by naming every section of the markdown document. Only the edge case of a nonexistent or unroutable slug is left unaddressed.

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% and the slug property already documents both the example value and 'leave out to list available skills,' so the description is largely restating structured data. Baseline 3 applies — the description adds no new syntax or format detail for the 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 verb and resource — 'Return the agent-ready ingestion skill for one data source as markdown' — and enumerates the exact payload sections (access, request, response format, snippet, limits, quirks, terms, sources). That makes it clearly distinct from siblings like get_entry or get_source_urls, which return catalog metadata rather than a skill document.

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?

Gives explicit conditional usage for the one parameter: 'Call it without a slug to list the sources that have a skill so far,' which tells the agent how to discover valid slugs before fetching. It does not, however, contrast itself with the sibling catalog tools an agent might otherwise reach for, so routing is inferred rather than stated.

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