track_thesis

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

Annotations already declare a non-read-only, non-destructive, closed-world write, and 'put a thesis on the scorecard' is consistent with that. The description adds no state semantics beyond it: no word on idempotency (what happens if the thesis is already tracked), whether prior entry price/date are overwritten, or what errors occur for an unknown thesis_id.

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?

A single sentence with no padding, leading with the action and then the measurement model. Everything stated is load-bearing for understanding what gets tracked.

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?

An output schema exists and the schema is well described, so return-value explanation is rightly omitted. But for a write tool with a hidden 'stop' branch and a required thesis_id that is never characterized (must the thesis pre-exist? must it be unresolved?), the description leaves real gaps an agent would hit in practice.

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 83%, with only thesis_id undocumented, so the schema carries most of the load and the baseline is high. The description still contributes by tying entry_price and entry_date together as the measurement origin and benchmark as the comparison leg, which explains why those three matter rather than just what they are.

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?

States a specific verb and resource: putting a thesis on the scorecard, tracked as return vs. a benchmark from an entry price/date. That is concrete enough to distinguish it from record_thesis (creation) and update_thesis (mutation), though those alternatives are never named, and the 'stop' mode of the same tool is not reflected in the purpose statement.

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?

No guidance at all on when to call this versus record_thesis, update_thesis, set_thesis_outcome or scorecard. The description also omits that passing stop=true reverses the operation, so an agent cannot tell from the prose that this tool both starts and stops tracking.

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