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

Annotations already declare destructiveHint=true and readOnlyHint=false, and the description goes beyond them with partial-update semantics, two failure modes (not-found for unknown/other-team, revoked links uneditable), and a non-obvious side-effect clarification that 'Existing Jams are not moved' when the folder changes. It still says nothing about authorization requirements or whether metadata replacement is recoverable, which matters for a destructive call.

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 the identifying verb and resource, then fields, then constraints and edge cases in short declarative sentences. Every sentence carries distinct information; nothing is restated from the schema verbatim beyond the field list needed to frame usage.

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 destructive 9-parameter mutation with no output schema, the description covers the semantics and failure modes well but omits what the call returns and what permissions are needed. An agent knows when to call it and what gets changed, but not what comes back or what auth level is required.

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 100%, so baseline is 3, but the description adds real meaning beyond the schema: the folder parameter is scoped to 'future recordings' and explicitly does not relocate existing Jams, and metadata is framed as a full replacement. The intent/llm_model bookkeeping parameters are not mentioned, which keeps it from a 5.

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+resource+identifier: 'Update a recording link by its publicId,' then enumerates exactly which fields can be modified (name, folder, Jam title, reference, expiration, metadata). This distinguishes it from createRecordingLink, getRecordingLink and deleteRecordingLink by verb alone, though no sibling is named explicitly.

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 'Use it to...' clause gives concrete use cases and the partial-update rule ('Only the fields you pass are changed') tells an agent it needn't send the full record. Failure conditions ('Unknown or other-team links return not-found; revoked links cannot be edited') are stated, but no explicit routing to getRecordingLink for reads or createRecordingLink for new links.

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