iranti

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes key behaviors: the tool writes durable facts (mutation), requires immediate calls (timing constraint), handles conflicts automatically ('Conflicts on the same entity+key are detected automatically and may be resolved or escalated'), and mentions personal-memory key handling. However, it doesn't cover error handling, rate limits, or authentication requirements, leaving some gaps for a mutation tool.

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?

The description is well-structured and front-loaded with the core purpose. Most sentences earn their place by providing critical guidance (timing, examples, conflict handling). However, it could be slightly more concise—some phrasing is repetitive (e.g., multiple 'before the next action' examples), and the paragraph format might benefit from bullet points for the timing examples.

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?

Given the complexity (mutation tool with 11 parameters, no annotations, no output schema), the description does a good job of covering essential context: purpose, timing, conflict handling, and parameter semantics. It adequately compensates for the lack of annotations and output schema by explaining behavioral traits and usage. However, it doesn't describe the return value or error responses, which would be helpful for a write operation.

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. The description adds meaningful context beyond the schema: it explains that 'confidence is optional and defaults to 85', clarifies the purpose of 'propertiesJson' ('when you need structured issue or workflow metadata such as issueStatus=open|resolved, severity, or resolution notes'), and mentions 'Personal-memory keys honor the configured canonical personal entity.' This provides valuable semantic guidance for several parameters, elevating the score above baseline.

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 clearly states the tool's purpose: 'Write one durable fact to shared memory for a specific entity.' It specifies the verb ('write'), resource ('durable fact'), and destination ('shared memory'), distinguishing it from siblings like iranti_query (read) or iranti_ingest (bulk). The description explicitly contrasts with batching/deferring, further clarifying its singular write operation.

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 description provides explicit, detailed guidance on when to use this tool: 'Call IMMEDIATELY when a fact is confirmed — do not batch or defer to end of turn.' It gives concrete examples (after editing a file, running a command, getting search results) and states the purpose ('when you learned something concrete that future turns, agents, or sessions should retain'). It also mentions alternatives implicitly by contrasting with batching/deferring, though it doesn't name specific sibling tools as alternatives.

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