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

With no annotations, the description carries the full burden and does disclose meaningful behavior: payload shape (audio URL + inhale/hold/exhale timeline), ~5 minute duration, voice and singing-bowl cues, and a documented fallback to exact phase timing when no recording exists for a language. It omits auth requirements, error cases, and whether the URL is time-limited, 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?

A single dense sentence front-loads the return value, then the fallback, then a short imperative. Every clause earns its place, though the sentence is long enough that the fallback condition is easy to miss on a skim.

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?

There is no output schema, so the description must explain the return value and does: audio URL, cue composition, approximate duration, timeline contents, and the no-recording fallback. Combined with a fully documented 6-parameter schema, an agent has enough to invoke this correctly.

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 100%, so the enum lists and per-parameter descriptions already do the work, and the baseline of 3 applies. The description adds only one marginally useful signal — that recording availability depends on the requested language, tying loosely to the lang and length params — and says nothing about pattern, voice, music, or binaural.

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 ('Get a ready-to-play guided breathing session') and enumerates what comes back: an audio URL plus a phase timeline. It implicitly separates itself from the list_* siblings by being the retrieval step, but never names them, so differentiation is inferred rather than stated.

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 'fetch the actual session' call after picking a pattern/language, but there is no explicit when-to-use, when-not-to-use, or pointer to list_breath_patterns for discovering valid pattern ids. The single imperative 'Show the attribution' is a post-call instruction, not selection guidance.

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