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

Annotations already declare the safe, idempotent, closed-world read profile, so the bar is lower. The description still adds real context beyond them: the transient "writing" state with a retry instruction, and the note that reading text is content for the person, which signals it should be surfaced rather than reinterpreted.

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?

Three short sentences, front-loaded with what is returned, then the async-state caveat, then the content-type note. No filler or repetition.

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, so return values need not be spelled out, yet the description still summarizes them and covers the one non-obvious runtime state ("writing"). Missing only error behavior for an invalid or inaccessible readingId.

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% and the single parameter already documents its provenance ('readingId from list_my_readings or get_birth_reading'). The description restates the id-based lookup without adding format, validity, or failure semantics, so 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?

States a specific verb and resource ('Returns one reading ... by readingId') and even enumerates the payload (sections and a celestio.ai link), so it is clearly distinct from list_my_readings. It never names the sibling explicitly, but the singular-by-id framing makes the split obvious.

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?

The only conditional guidance is the "writing" status retry hint, which is genuinely useful. There is no explicit statement of when to reach for this versus get_birth_reading or list_my_readings, and no mention of what happens with an unknown or foreign readingId.

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