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 does well: it discloses that the feed is curated (not exhaustive), that the Assetize interpretation is 'clearly-labelled' and 'never presented as IBM's', and that each record includes sources and corpus records. This is significant behavioral context—it tells the agent that the tool returns interpreted analysis, not just raw data, and that the interpretation is clearly separated from IBM's official stance. It also implies a read-only operation (no side effects mentioned). The only minor gap is not stating pagination or error behavior, but the description is quite transparent for a read-only list/detail 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 a single, dense paragraph that front-loads the core value proposition ('curated feed of genuinely material IBM Maximo / MAS 9.x changes') and then lists the key attributes in a compact, scannable list. Every sentence earns its place: the first sentence defines the scope and content, the second explains the data structure, the third gives usage instructions, and the fourth provides a reference to the same data online. No fluff, no repetition of schema details. It is appropriately sized for a tool with this complexity.

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 tool's moderate complexity (3 optional params, no output schema, no annotations), the description is quite complete. It explains the two modes (detail vs list), the filtering option, the content of each record, and the provenance of the data. The only missing context is what the output looks like (no output schema) and any rate limits or pagination behavior, but the description's mention of 'limit' and 'default 30, max 60' in the schema partially covers that. For a read-only feed tool, this is nearly complete. A 5 would require explicit output format details or explicit sibling differentiation, so 4 is appropriate.

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 schema already documents all three parameters (slug, limit, category) with descriptions. The description adds value by explaining the relationship between slug and listing mode ('Pass a slug for one change in full; omit it to list'), which is not fully captured in the schema's individual parameter descriptions. It also adds the category filter context. However, the description doesn't add detail on the limit parameter's default/max (though the schema does), so the description's added value is moderate. Baseline 3 for 100% coverage, plus the mode-switching explanation, justifies a 4.

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: it provides a curated feed of material IBM Maximo/MAS 9.x changes, with a specific verb ('Pass a slug... omit it to list') and resource ('curated feed'). It distinguishes itself from siblings by emphasizing 'curated' and 'genuinely material' changes, and by describing the unique data structure (What Changed / Why It Matters, version comparison, Assetize interpretation). This is a specific, actionable description that an agent can use to select this tool over alternatives like maximo_changelog or deprecation_register.

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 clear usage context: 'Pass a slug for one change in full; omit it to list, optionally filtered by category.' This tells the agent exactly how to invoke the tool for two modes (detail vs list). It also mentions the data is the same as assetize.com.au/change-watch, which gives context. However, it doesn't explicitly state when to use this tool versus siblings like maximo_changelog or deprecation_register, nor does it state exclusions (e.g., 'use deprecation_register for a full deprecation list'). The usage is implied by the 'curated' and 'material' framing, but not explicitly contrasted with alternatives.

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