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

Annotations already declare destructiveHint=false, openWorldHint=false and idempotentHint=false, so the safety profile is covered. The description adds genuinely useful context beyond that: a fixed $0.10 per-call charge, which matters because the call is non-idempotent and retries cost money. It says nothing about transcript length limits, language handling, or why readOnlyHint is false (presumably usage/billing writes).

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 the core action, zero structural waste. 'A quick read of a long recording' is the weakest line but still carries a use-case signal rather than pure filler.

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?

Context is simple: one required string parameter, no output schema, no nested objects, flat annotations. The description covers action, cost, and intent, which is enough for an agent to call it correctly; the missing return-format detail is excused by the absence of an output schema only insofar as the shape is predictable ('key points').

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?

One parameter with 0% schema description coverage, so the description must carry the load. 'Summarise a transcript' implies the input is raw transcript text, but it adds no constraints on format, length, timestamps, or language, so the agent still has to guess what a valid transcript looks like.

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: 'Summarise a transcript into key points', which separates it from siblings like fikra_summarise_contract and fikra_summarise_research by input type. Minor friction: the tool is named 'summarise_audio' but the description only ever refers to a transcript, so an agent may briefly wonder whether it accepts audio files.

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?

'A quick read of a long recording' implies the use case (long input, want a condensed read) but names no alternatives and gives no when-not conditions. With fikra_generate_meeting_minutes and fikra_extract_meeting_actions as nearby siblings, an agent gets no routing guidance between summarising and structured extraction.

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