workspace_read_source_blocks

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

With no annotations, the description carries the full burden. It does disclose useful behavior beyond the schema: pagination via a 'next until null' cursor, that blocks are raw text with no inferred proof ownership, and that reading does not mutate reading data. It omits error/auth/rate-limit behavior, so it is partial rather than rich.

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?

Short and front-loaded: the core operation leads, with pagination and caveats trailing. Each sentence carries distinct information (operation, return nature, compatibility, invalidation), though the phrasing is terse.

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 tool with no output schema and no annotations, the description is only moderately complete: it conveys return nature and pagination but not the shape of the returned blocks or how to obtain the starting locator. It covers the essentials for calling but leaves gaps an agent would need to close.

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%, so the description must document both parameters. It hints at span_id by calling it a 'slice locator' and at pagination via 'follow next', but the 'limit' parameter (default 20, max 50) is never mentioned, leaving half the parameters unexplained in both schema and description.

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 ('Read raw source blocks') plus the input it draws from ('from a slice locator'), so the agent knows this returns source text rather than results or proofs. It does not name the likely sibling producer of that locator (workspace_get_source_slice), so sibling differentiation is left implicit.

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?

Usage is only implied: 'from a slice locator' signals a prerequisite locator exists, and 'follow next until null' describes the pagination loop. There is no explicit when-to-use/when-not statement and no named alternative among the many workspace_get_* siblings.

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