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

Annotations already flag non-read-only, non-idempotent behavior; the description adds concrete side effects: it sends emails, may send phone push after app install, and creates a НамериМиДом.bg account if absent. This is useful disclosure of persistent mutation, though it does not mention duplicate-subscription or cancellation behavior.

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 main behavior is front-loaded, and the trigger phrases and side-effect note earn their place. The bilingual Bulgarian repetition adds length but supports the local user base without obscuring the key information.

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 9-parameter mutating subscription tool without an output schema, the description covers the essential call context: main effect, delivery channels, account creation side effect, user info to collect, and trigger phrases. It leaves minor gaps such as how to map a prior search into the criteria and what to tell the user after a successful subscription.

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?

The description clarifies that name and email must be collected first and that the other parameters are the 'criteria' defining the saved search. However, with only 44% schema description coverage, it does not compensate for the undocumented filter fields (city, neighborhood, currency, transaction, property_type) beyond calling them criteria.

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?

States a specific action: subscribe the user to a saved search, and defines the trigger behavior ('whenever a NEW listing matching these criteria appears') plus the delivery channel. This distinguishes it from sibling search/match tools: it is not one-off search (search_properties) or match checking (check_new_matches) but an ongoing alert subscription.

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?

Gives explicit when-to-use trigger phrases ('notify me', 'let me know when something new appears', 'keep looking for me') and a required precondition ('Ask for their name and email first...'). It does not state when not to use it or name alternative tools, so it stops short of full routing guidance.

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