Assess to-do

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

With no annotations, the description carries the full burden, and it does disclose non-obvious dual-mode behavior plus the fact that a verdict is stored (a mutation). It omits what the evidence package contains, what happens to a previously stored verdict, and what permissions or preconditions the write requires.

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?

Two tightly written sentences, with the core function front-loaded and the branching behavior second. No filler, but the undefined 'axes a-d' shorthand costs a little clarity within that compact frame.

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?

There is no output schema, no annotations, and the tool performs a write (stores the verdict), so the description should carry more: what the evidence package looks like, how the assessment is consumed downstream, and what 'axes a-d' means. It covers the branching model well but leaves the payload and result semantics undefined.

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 `todo_id` parameter is documented as 'The id from list_todos', so the schema does the work. The description adds no format, provenance, or validity detail beyond what the schema already states; baseline 3 applies.

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?

Names a specific verb+resource ('Effort assessment for one to-do') and hints at sibling differentiation by naming `save_assessment`. However, 'axes a-d' is unexplained jargon that an agent cannot act on without outside knowledge, so it is clear but not fully self-contained.

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?

Explains the two operating contexts: sampling-capable clients get the verdict stored directly, others receive an evidence package destined for `save_assessment`. That routing is genuinely useful, though it never states when an agent should avoid this tool or whether re-assessment is expected.

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