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

Beyond the readOnlyHint annotation, the description adds rich behavioral detail: newest-first ordering, token budgeting, derived from recorded decisions so it cannot rot, and superseded decisions never appear. It also clarifies that lines are context, not instructions. No contradiction with annotations.

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?

Three sentences, front-loaded with the trigger condition, and each sentence serves a distinct purpose: when to call, what it returns, and how to interpret the output. No redundancy or filler.

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 read-only tool with no output schema, the description covers return content, ordering, freshness, token budget behavior, and interpretation guidance. The agent has enough to call it correctly and understand the response. Schema and annotations cover the rest.

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 100%, so the baseline is 3. The description adds a small amount of meaning by saying to scope it to a project or task, which reinforces the purpose of taskId and project, but it does not add syntax or format details beyond the schema.

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 description states exactly what the tool returns: the workspace's live decisions and lessons, packed to a token budget, newest first. It distinguishes itself from siblings by noting it is derived from recorded decisions and that output is context about past choices, not instructions. The verb 'returns' and the specific resource 'context digest' are clearly identified.

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?

It explicitly says to call this at the START of non-trivial work and advises scoping by project or task. It implies a distinction from record_decision (which creates decisions) but does not name alternatives explicitly or give a when-not-to-use condition beyond 'not instructions.' The guidance is strong but not exhaustive.

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