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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered; the description adds real semantic detail beyond that: the board is ordered by 'worth', it surfaces regressions ('what slipped back'), and it embeds the domain rule that a fix only counts as done once a later read finds it passing. It does not mention size limits or whether the list is truncated, which keeps it below a 5.

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?

It is a single dense sentence with no filler, so it is compact, but the front-loaded clause buries the plain meaning under a 'progress page' metaphor. The most useful line, the definition of done, is stranded at the end after a list of mostly decorative labels.

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?

With no parameters, no output schema, and permissive annotations, the description carries the whole burden of explaining what comes back. It does name the content sections, which is the minimum an agent needs, but gives no sense of ordering stability, volume, or item shape, so it is adequate rather than complete.

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?

The tool takes zero parameters, which is the baseline-4 case; there are no argument semantics to explain. The description correctly implies the call is context-free (scoped to 'the person's' own sites) rather than parameterized.

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 name and title say 'todo' / 'work board', and the description enumerates what the board holds (next fix, other fixes by worth, regressions, verified fixes, sites needing re-read). However, everything is expressed in metaphor ('what slipped back', 'the words to work from', 'by worth'), so an agent must decode terms rather than read a plain statement of purpose. It also never distinguishes itself from similarly-scoped siblings like mttr_queue, mttr_content_next, or mttr_plan.

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?

There is no explicit statement of when to call this versus alternatives, and no prerequisites or exclusions. The only implicit cue is that it is a dashboard-style summary of current work, but the agent has to infer that calling this is the way to find out what to do next.

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