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

With no annotations supplied, the description carries the full burden and does so well: it discloses the async contract (job_id returned immediately, status running or queued when the server is full), the 1-3 minute latency, and the required follow-up call to get_presentation for status and download links. It also surfaces plan-level constraints (free plan limited to vazirmatn and slide counts of 5 or 10; pptx source requires Pro), which an agent cannot infer from any structured field.

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?

Front-loaded with purpose and the return contract, then moves into parameter semantics in a logical order, with zero filler. The single input_mode sentence is dense and runs long, but every clause carries information an agent would otherwise have to guess.

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 15-parameter, no-output-schema, no-annotation creation tool, the description covers the three things an agent could get wrong: which mode to pick, that the call is async and needs polling, and what plan restrictions apply. Nothing essential to a correct first invocation is missing.

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 80%, so the baseline is 3, and the description earns above that by explaining what each mode actually does to the content ("its substance becomes slides with nothing added, side talk and repetition dropped") plus per-mode character ranges (20-2000, 120-30000, 40-30000) that the schema does not encode as minLength/maxLength. It also clarifies that exact_text only applies to full_text. The goal, audience and theme parameters get no added meaning, but their enums are largely self-describing.

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?

Opens with a specific verb and resource ("Start building a Persian presentation deck") and immediately establishes it as an async job producer, which separates it from get_presentation, list_presentations and restyle_presentation. An agent can identify the tool's role without opening the schema.

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?

Gives explicit selection criteria among the three input_mode values (topic for a short description, full_text for a finished document, partial_text for a draft to be completed) and routes polling to get_presentation and id lookups to list_design_options. It never contrasts itself with restyle_presentation, which is the alternative path for an existing deck, so the when-not is incomplete.

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