source_read

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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false), yet the description adds substantial beyond-schema behavior: content is always bounded at 10,000 chars by default, max_chars/offset page as a slice while char_count stays the full length, content is null when the source isn't ready, and output_format=markdown requires the server's markdownify extra. That is far more than the annotations provide; only the return of errors/failure modes is left unstated.

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 resource, then organized by parameter with the default marked inline. Dense and slightly repetitive ('bounded'/'caps'/'page'), but essentially every sentence carries operational information an agent needs.

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 exists, and the description compensates by specifying the exact return shape for both detail levels, including field names, the truncation flag, and the null/zero-char case. For a 6-parameter read tool, nothing an agent needs to call it correctly is 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 description coverage is 0% and there are 6 parameters, so the description must carry the load, and it does for four of them: detail's two return shapes, max_chars' 10k default cap, offset's slice semantics, and output_format's markdownify dependency and restriction to detail=full. The required notebook/source params get only 'accepts a notebook/source name or ID', which is thin but adequate.

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 first sentence states a specific verb (read) and resource (source) and immediately scopes it to two named detail levels. It also declares the accepted identifier forms (notebook/source name or ID), so an agent can distinguish it from source_list, source_wait, and chat_ask without opening any schema.

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?

Explicit routing guidance: summary is for cheap low-token triage across many sources, full is the default for actual content, and the description closes with 'Prefer chat_ask for querying large sources rather than pulling the whole body' — a named alternative plus the condition that selects it.

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