Save TIA Analysis Note

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

Beyond the annotations, the description discloses genuinely useful behavior: the note is scoped to the export cache, bound to the current export signature, and automatically marked stale after program changes. That staleness lifecycle is not derivable from readOnlyHint=false / idempotentHint=true / destructiveHint=false, so it adds real value. It is silent on overwrite semantics for an existing note at the same signature and on return values, keeping it below 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?

Two sentences, front-loaded with the action and destination, with no filler. The second sentence is dense but each clause carries distinct information (binding and staleness).

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 six-parameter mutation tool with zero schema description coverage and no output schema, the description leaves the agent without enough to populate subject, summary, facts, or confidence correctly. Annotations cover the safety profile, but the parameter and note-lifecycle gaps are substantial.

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% across six parameters, so the description must compensate and it largely does not. Only 'evidence' and 'exportDir' are indirectly evoked ('evidence-backed', 'export cache' / 'export signature'); subject, summary, facts, and especially the confidence enum (verified/mixed/inference) get no explanation of meaning or expected content.

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 uses a specific verb ('Persist') and a specific resource ('an evidence-backed engineering explanation') and states where it lands (under the export cache). It is clearly distinguishable from the read-side sibling by implication, but it never names tia_search_analysis_notes or any alternative, so sibling differentiation relies on the reader's inference.

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 rationale 'so a stronger model can analyze once and later models can reuse it' implies the usage context (cache expensive analysis), but there is no explicit when-to-use trigger, no when-not-to-use condition, and no named alternative for retrieving the note later. Guidance is implied rather than stated.

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