What NVDA said

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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds a genuinely non-obvious behavioral fact: speech is captured even when the user has speech turned off, so the history reflects what NVDA would say. It stops short of disclosing buffer capacity, retention, or whether entries are ever dropped.

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 short sentences, front-loaded with the core action and ordering, followed by the one piece of context an agent could not infer. No filler or redundant restatement of the name.

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-value explanation is unnecessary, and all four parameters are documented in the schema with annotations covering safety. For a simple read tool the definition is nearly complete; only sibling disambiguation and buffer/retention limits are absent.

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 100%, so limit, after_id, contains and response_format are all fully documented structurally. The description only restates the id-based polling idea already spelled out in after_id's schema text, adding no new syntax or semantics; 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?

Uses a specific verb and resource ("Return what NVDA has spoken"), plus ordering ("newest last") and the polling affordance. It does not distinguish itself from near-neighbours like nvda_get_output_history, nvda_preview_speech or nvda_wait_for_speech, which an agent must resolve on its own.

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 phrase "with ids for incremental polling" implies the intended usage pattern (poll with after_id to get only new speech), but the description never states when to choose this over nvda_wait_for_speech, nvda_preview_speech or nvda_get_output_history, nor any when-not condition.

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