Read the workspace memory

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered and the trailing "Read-only" is largely redundant. The description still earns credit for disclosing the payload's subject matter and the whole-vs-section retrieval behavior, which the annotations say nothing about. It stops short of describing the returned format or size, keeping it out of 5 territory.

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 resource and its contents, followed by two short imperative sentences. Every clause carries information except the trailing "Read-only", which restates the readOnlyHint annotation and could be dropped.

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 zero-required-parameter, single-optional-parameter read tool with no output schema, the description covers what is returned and how to scope it, which is enough to call it correctly. It leaves the serialization of the memory (plain text, markdown, structured sections) unspecified, which is the one remaining gap.

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 single optional `section` parameter is documented with an example, so the baseline would be 3. The description adds real meaning by making clear that omitting the parameter returns the full memory while supplying it scopes to one heading — behavior an agent cannot infer from the schema alone.

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?

"Returns the workspace memory" is a specific verb+resource, and the parenthetical enumerates exactly what the memory contains (naming, groups, proxy rules, working hours, never-do list). The clause "or one section of it by heading" defines the scoped variant, which cleanly separates it from update_memory and workspace_summary.

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?

"Read this before acting" is an explicit, actionable when-to-use directive rather than implied guidance. It does not name a sibling alternative (e.g. update_memory for writes), but the read/write split is obvious from the names and the tool's own framing.

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