get_durability

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

Annotations only cover readOnlyHint and openWorldHint, and the description adds real behavioral context on top: it states the output is statistics-only with no verdict, that sessions failing the quality filter are counted per exclusion reason, that samples under 8 are flagged, and that mixed indoor/outdoor or mixed equipment are noted. It stops short of describing limits like rate limits or exact return fields, but the disclosure is substantive.

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 dense and heavily parenthesized, but the primary purpose is front-loaded and the length is justified by 13 parameters and nontrivial filter/output semantics. A few parenthetical clauses could be trimmed, but every block of content is relevant.

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 13-parameter analysis tool with no output schema, the description covers the metric, the filter logic, the reported statistics, the small-sample and mixing caveats, and the machine-readable option. Return value shape is left to the output_format/detail_level parameters rather than the description, which is acceptable but leaves some detail implicit.

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 already 100%, so the baseline is 3, but the description adds genuine meaning about how the parameters operate: the quality-filter semantics (min_minutes, stops, max_vi, max_temp_c, environment), the default 6-week window, and the framing of drift_threshold_pct as the commonly cited 5%. That goes beyond restating schema text.

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 analysis (aerobic decoupling power:HR / pace:HR plus efficiency-factor trend) applied to steady long cycling and running sessions, and it explicitly differentiates itself from get_power_hr_efficiency ('Per interval and bike'). An agent can tell exactly what this computes and how it differs from the neighboring efficiency tool.

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?

It opens with 'Use for aerobic durability' and routes the agent to get_power_hr_efficiency when per-interval/per-bike granularity is needed and to get_guide for the method. That is clear alternative routing, though it does not spell out explicit when-not conditions (e.g., data prerequisites such as needing HR or long steady sessions).

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