Read what is inside cards

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

Far exceeds the annotations: it discloses cost attribution (paid_by), per-tool quota (at most 20/day), caching (saved readings return instantly and spend nothing, refresh:true forces new), side effects (new readings pinned beside cards, one Ctrl+Z removes them), a ~40s latency contract returning still_reading with retry_after_seconds, and that content is fenced as data, never instructions. readOnlyHint=false is consistent with the pinning behavior described.

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?

It is front-loaded and most sentences carry load-bearing behavior, but it is a single ~250-word run-on dense with parentheticals, and a few asides ('the way its Read contents does', 'Authors are what each card records, unverified') add bulk without changing agent behavior. Splitting mode/return/limits into distinct sentences would help.

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 carries the full return-format burden and does so: it explains the saved-vs-app-mode answer, fencing and provenance marking, full/partial status, embedded files resolved as text/image/local path, and the 'Tell the user' relay sentence for unreadable cards. Nothing an agent needs to invoke or interpret the call 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 100%, so the baseline is 3, but the description adds real meaning: max_chars caps the whole answer at 48,000 (not just per card), card_ids must be the ids read_canvas prints, entry_paths must be paths from the folder's own listing, and pin_result/wait_seconds are inert when reading saved files. These clarify cross-parameter interaction beyond the schema text.

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?

The opening states a specific verb and resource ('Read what is INSIDE cards on a KLYPIX canvas') and immediately enumerates the card types it covers (reel, YouTube video, web page, media, PDF/Office, text, folder). It also routes the agent by naming where the ids come from (read_canvas, klypix_status), distinguishing it from those siblings.

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?

It gives concrete selection rules: pass up to 5 card ids as read_canvas prints them, or the ids klypix_status lists to read the current selection; use refresh:true for a new reading; use entry_paths for folder cards. What is missing is an explicit when-not/alternative statement (e.g. use read_canvas or canvas_view instead when you only need structure).

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