rec_read

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds genuinely non-inferable behavior: the wide pivot produces one row per event with selected symbols forward-filled, and it works on finished recordings from earlier sessions (persistence). It omits max_rows truncation semantics, which would have earned a 5.

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 sentences, front-loaded with the core action and the mode flag, with no filler. The quoted parenthetical is slightly chatty but it usefully anchors the wide mode to an intent.

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 described, and the description adequately frames the windowed read and persistence. But with 0% schema coverage across five undocumented parameters, an agent still lacks enough to call it correctly beyond the default id-only read.

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 0% for 6 parameters, so the description carries the full burden and only explains 'wide' (and implicitly 'symbols'). The meanings, formats, and defaults of id, t_from_ms, t_to_ms, and max_rows — notably whether times are ms offsets or absolute and what happens past max_rows — are left entirely undocumented.

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 ('Read a time window of a recording from its file'), which is unambiguous against siblings like rec_list, rec_export, or rec_delete. It does not explicitly name an alternative sibling, so it stops short of full differentiation.

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?

Provides usage context for the wide flag ('what you want for "what else was true when X happened"') and notes it works on finished recordings from earlier sessions, which implies reading past data vs a live snapshot. However, it never says when to prefer this over rec_snapshot, rec_export, or ads_read, and gives no exclusions.

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