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

Annotations only say readOnlyHint=false / destructiveHint=false, so the description does the heavy lifting and does it well: it discloses the side effect of clearing a task from the review queue, that records are immutable, and that change is expressed via supersedesId rather than edits. It stops short of stating auth/permission requirements or any failure behavior, hence not 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?

Front-loaded with the 'two uses, one table of record' frame, then cleanly enumerated as (1) and (2), so the agent can stop reading once it identifies the mode. Dense and mostly waste-free, though rhetorical asides like 'you are the messenger, not the decider' cost a little length for their guardrail value.

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 14-parameter mutation tool with no output schema, the description covers both modes, immutability, supersession, and the downstream consumer (get_context). The one gap is the required-field discrepancy: the schema requires only 'options', while the prose states outcome is required with title, which could cause a validation surprise.

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 100%, so the baseline is 3, but the description adds real routing value the schema cannot: it maps which parameters belong to which mode (id+decision+note for verdict relay; title+outcome+MADR fields for a standalone record). One inconsistency remains — the schema marks only 'options' as required while the prose treats title+outcome as the required record pair.

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 description states a specific verb+resource ('record a decision') and then splits it into two explicitly named modes — relaying a user verdict on a task versus recording a standalone durable decision. It also names the reading counterpart (get_context), so an agent can distinguish it from siblings like update_task or complete_task 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?

Explicit when-to-use for both modes ('whenever the user makes a real choice in conversation'), an explicit when-not ('Never call this to accept your own work: you are the messenger, not the decider'), and a stated anti-pattern ('the user did not object is not a decision'). Alternative-driven routing to get_context is named for the read side.

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