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

With no annotations, the description bears the full behavioral burden. The untrusted-content warning for *_untrusted and Commons fields is genuinely valuable security context that is not derivable from the schema, and "Read" signals a safe non-mutating operation. However, it never describes what the summary actually returns (metrics, lesson fields, recency window) or whether results are truncated, which a no-annotation, no-output-schema tool should cover.

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, purpose front-loaded, zero filler. The second sentence is dense but earns its place as a safety instruction; the only weakness is that the security caveat occupies prose space that could have partly gone to return-value description.

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 simple one-parameter read tool with no output schema, the description is minimally adequate: it names the scope and adds an important untrusted-data caveat. It still leaves the agent guessing about what the returned summary looks like and about the default behavior when no season is supplied.

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 0%, so the description must carry the single parameter. "Optionally for one season" usefully conveys that the parameter is optional and that it narrows to a single season, but the schema already names it "season" and enforces UUID/pattern constraints that the description does not clarify (e.g., whether an omitted season means all seasons or current season).

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?

"Read my calibration summary and recent lessons, optionally for one season" states a specific verb (read) and two concrete resources (calibration summary, recent lessons), plus a scoping option. It is distinguishable from forecast-oriented siblings like my_forecasts or get_leaderboard, though it never explicitly contrasts itself with ledger_similar or read_commons.

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?

Usage is only implied: an agent gathers that this is the way to view its own calibration record, and that the season filter is optional. There is no explicit when-to-use vs. when-to-use-a-sibling guidance (e.g., ledger_similar vs. ledger_summary), which matters given a crowded ledger/forecast family of tools.

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