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

The annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, fully specifying the safety profile. The description adds no additional behavioral context like whether results are cached, how Ofsted grades are sourced, or any rate limits. With annotations taking the lead, a 3 is appropriate.

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 comprehensive sentence, front-loading the usage scenario and then listing compared attributes. It is efficient and has no wasted words, though the long list of attributes could be seen as slightly dense.

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 there is an output schema, the description doesn't need to detail return values. It covers the purpose, source of ids, and comparison scope sufficiently. However, it could mention that exactly two to four ids are required (the schema has constraints but the description only says 'two to four'), and it doesn't address error handling or invalid IDs. Mostly complete.

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%; the single parameter home_ids is fully documented with its source ('Ids from search_homes') and constraints (min 2, max 4 items). The description mentions 'two to four homes' which restates the schema constraints but adds no extra meaning like ID format or edge cases. Baseline 3 is correct.

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 ('compare') and resource ('homes') and enumerates exactly what attributes are compared (price, rooms, schools, Ofsted grade, station, etc.). It also names the sibling tool 'search_homes' as the source of the ids, which clearly distinguishes it from get_home and get_area_guide.

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?

It provides clear context: 'use this when the user wants to compare two to four homes from search_homes results side by side.' The reference to search_homes gives the alternative source. However, it doesn't explicitly say when not to use this tool (e.g., comparing more than four homes, or single-home details), so a slight gap remains.

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