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 one substantive behavioral trait: it only returns archived data and cannot reconstruct unrecorded history. It says nothing about ordering of snapshots, what a snapshot contains, pagination interaction with the limit parameter, or permission requirements, leaving meaningful gaps for a read tool with no 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?

Two sentences, no filler, and the function of the tool is front-loaded before the archive caveat. Every clause carries information the agent needs.

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?

The description covers provenance and a critical limitation, which is the important part. But with no output schema and four parameters, an agent still does not know the shape of a returned snapshot (probabilities? timestamps? per-team breakdowns?) or how results are ordered when limit truncates them.

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 all four parameters are already documented in the schema (team, limit, league, datasetName). The description adds only the example framing around datasetName that the schema already provides, so the 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?

The description names a specific resource and dimension: probability movement across a season, retrieved from a named archive dataset. It is clearly a historical-read tool, which differentiates it in spirit from the current-state siblings like get_team_probabilities, though it never names them explicitly.

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?

A key prerequisite is stated — the data must have been produced by Actors running with archiveToNamedDataset set — which implicitly tells the agent when this tool will return results. However, there is no explicit guidance on when to choose this over get_league_probabilities or get_team_probabilities, nor any stated exclusions beyond the archive limitation.

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